DETAILED ACTION
Applicant has amended claims 1, 3, 4, 7-10, 13-16, 19-22, 25-28, 31-34, 37-40, 43-46, 49, 51, 55, 57, 58, 61, 63, 64, 67, 69, 73, 75, 79, 81, 85-91, 93, 94, 97, and 99. Claims 103-104 are new. Claims 1-104 are pending.
Response to Arguments
Applicant’s arguments filed on April 1, 2026 regarding pending claims have been considered but are moot in view of the new ground(s) of rejection. The amended claims resulted in changes to the scope and contents and raised new matter and indefiniteness issues; therefore, the grounds of rejection are modified accordingly, as indicated further below. It is noted that prior arts previously applied in the last Office action (OA) that are currently not relied upon remain pertinent to applicant’s disclosure.
Specification
The specification is objected to as failing to provide proper antecedent basis for the claimed subject matter. See 37 CFR 1.75(d)(1) and MPEP § 608.01(o). Correction of the following is required:
Claim 1 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 7 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-9 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 13 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 19 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 25 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 31 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-10 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 37 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 43 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 49 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 55 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 61 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 67 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-10 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 73 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 79 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-10 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 85 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 91 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 97 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-11 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
New claim 103 recites the limitation “wherein spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters and spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” in lines 1-5 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
New claim 104 recites the limitation “wherein generating the one or more affine transformation parameters comprises generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions of one or more activation maps according to the one or more semantic labels” in lines 1-4 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-104 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention.
Claim 1 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 2-6 and 103-104 are rejected by virtue of being dependent upon rejected base claim 1.
Claim 7 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-9 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 8-12 are rejected by virtue of being dependent upon rejected base claim 7.
Claim 13 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 14-18 are rejected by virtue of being dependent upon rejected base claim 13.
Claim 19 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 20-24 are rejected by virtue of being dependent upon rejected base claim 19.
Claim 25 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 26-30 are rejected by virtue of being dependent upon rejected base claim 25.
Claim 31 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-10 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 32-36 are rejected by virtue of being dependent upon rejected base claim 31.
Claim 37 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 38-42 are rejected by virtue of being dependent upon rejected base claim 37.
Claim 43 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 44-48 are rejected by virtue of being dependent upon rejected base claim 43.
Claim 49 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 50-54 are rejected by virtue of being dependent upon rejected base claim 49.
Claim 55 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 56-60 are rejected by virtue of being dependent upon rejected base claim 55.
Claim 61 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 10-11 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 62-66 are rejected by virtue of being dependent upon rejected base claim 61.
Claim 67 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-10 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 68-72 are rejected by virtue of being dependent upon rejected base claim 67.
Claim 73 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 74-78 are rejected by virtue of being dependent upon rejected base claim 73.
Claim 79 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-10 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 80-84 are rejected by virtue of being dependent upon rejected base claim 79.
Claim 85 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-8 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 86-90 are rejected by virtue of being dependent upon rejected base claim 85.
Claim 91 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-9 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 92-96 are rejected by virtue of being dependent upon rejected base claim 91.
Claim 97 now recites the limitation “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-11 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in the disclosure, as originally filed.
Claims 98-102 are rejected by virtue of being dependent upon rejected base claim 97.
New claim 103 recites the limitation “wherein spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters and spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” in lines 1-5 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters and spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output, and hence are uniform across spatial coordinates… the normalization layer applies a spatially-varying affine transformation… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region… semantic layout can then be generated 512 using the labeled regions of the image space”.
However, the examiner was not able to find support for the claimed feature limitations “wherein spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters and spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” in the disclosure, as originally filed.
New claim 104 recites the limitation “wherein generating the one or more affine transformation parameters comprises generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions of one or more activation maps according to the one or more semantic labels” in lines 1-4 of the claim.
Applicant asserts that “Support for all amended claims can be found in the specification, and no new matter has been added by these amendments… The amendments are supported by the specification and do not add new matter” (Remarks, Pgs. 23 and 28).
However, the examiner was not able to find support for the claimed feature limitations “wherein generating the one or more affine transformation parameters comprises generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions of one or more activation maps according to the one or more semantic labels” in the original disclosure.
Par. [0014-24] of the specification of this application indicate “semantic layout will include two or more regions identified by the user, such as through the input of region boundaries. The user can also associate a semantic label (or other identifier) with each region, to indicate a type of object(s) to be rendered in that region… The semantic labels applied to various regions can be used to select the types of objects to be rendered”. Par. [0030-40] of the specification of this application also indicate “normalized activations are de-normalized to modulate the activation by an affine transformation whose parameters are inferred from external data… the affine parameters are used to control the global style of the output… the normalization layer applies a spatially-varying affine transformation… segmentation mask can be defined by… a set of integers denoting the semantic labels… Each entry in m denotes the semantic label of a pixel… The affine parameters of the normalization layer can depend on the input segmentation mask and vary with respect to the location (y, x)… the affine parameters are adaptive to the input segmentation mask… the learned affine parameters of SPADE provide enough signal about the label layout… The affine parameters of the normalization layers are learned using SPADE… a selection of a label for the region can be received 506, where the label is a semantic label (or other such designation) indicating a type of object to be rendered for that region… semantic layout can then be generated 512 using the labeled regions of the image space”.
However, the examiner was not able to find support for the claimed feature limitations “wherein generating the one or more affine transformation parameters comprises generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions of one or more activation maps according to the one or more semantic labels” in the disclosure, as originally filed.
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-104 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 6-9 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 2-6 and 103-104 are rejected by virtue of being dependent upon rejected base claim 1.
Claim 7 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 5-9 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 8-12 are rejected by virtue of being dependent upon rejected base claim 7.
Claim 13 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 14-18 are rejected by virtue of being dependent upon rejected base claim 13.
Claim 19 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-9 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 20-24 are rejected by virtue of being dependent upon rejected base claim 19.
Claim 25 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 26-30 are rejected by virtue of being dependent upon rejected base claim 25.
Claim 31 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 32-36 are rejected by virtue of being dependent upon rejected base claim 31.
Claim 37 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 38-42 are rejected by virtue of being dependent upon rejected base claim 37.
Claim 43 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-9 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 44-48 are rejected by virtue of being dependent upon rejected base claim 43.
Claim 49 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 6-8 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 50-54 are rejected by virtue of being dependent upon rejected base claim 49.
Claim 55 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 6-8 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 56-60 are rejected by virtue of being dependent upon rejected base claim 55.
Claim 61 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 9-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 62-66 are rejected by virtue of being dependent upon rejected base claim 61.
Claim 67 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-10 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 68-72 are rejected by virtue of being dependent upon rejected base claim 67.
Claim 73 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 6-8 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 74-78 are rejected by virtue of being dependent upon rejected base claim 73.
Claim 79 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-10 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 80-84 are rejected by virtue of being dependent upon rejected base claim 79.
Claim 85 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 6-8 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 86-90 are rejected by virtue of being dependent upon rejected base claim 85.
Claim 91 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 7-9 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 92-96 are rejected by virtue of being dependent upon rejected base claim 91.
Claim 97 now recites the limitation “one or more semantic labels of one or more regions in one or more semantic layout map inputs to the one or more neural networks, wherein the one or more affine transformation parameters include different parameter values for different regions corresponding to the one or more semantic labels” in lines 8-11 of the claim. However, it is not clear if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, or if the claimed “different regions corresponding to the one or more semantic labels” recited in the claim encompass embodiments corresponding to other “different regions corresponding to the one or more semantic labels” different from the claimed “one or more regions in one or more semantic layout map inputs” previously recited in the claim, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Claims 98-102 are rejected by virtue of being dependent upon rejected base claim 97.
New claim 103 recites the limitation “wherein spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters and spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” in lines 1-5 of the claim. However, the claimed “spatial locations” term in the claimed “spatial locations of one or more activation maps corresponding to a first region of the one or more semantic layout map inputs use a first set of affine transformation parameters” and “spatial locations corresponding to a second region of the one or more semantic layout map inputs use a second set of affine transformation parameters different from the first set” recited in lines 1-5 of the claim, respectively, is not defined in the claims, or anywhere else in the specification, as indicated above, and it is not clear if the claimed “spatial locations” term encompass embodiments corresponding to “spatial” sites, “spatial” regions, “spatial” sections, “spatial” places, or “spatial” areas, for example, or if the claimed “spatial locations” term encompass embodiments corresponding to “spatial” positions, “spatial” points, or “spatial” coordinates instead, for example. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
New claim 104 recites the limitation “wherein generating the one or more affine transformation parameters comprises generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions of one or more activation maps according to the one or more semantic labels” in lines 1-4 of the claim.
However, the claimed “parameter maps” term in the claimed “generating one or more parameter maps that assign different affine transformation parameter values to different spatial regions” recited in lines 1-4 of the claim, respectively, are not defined in the claims, or anywhere else in the specification, as indicated above. Therefore, the metes and bounds of the claim are not clearly set forth and the examiner cannot clearly determine which elements are encompassed by the claim language, which renders the claim indefinite.
Conclusion
Applicant’s amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GUILLERMO RIVERA-MARTINEZ whose telephone number is 571-272-4979. The examiner can normally be reached on Monday-Friday (8am - 5pm Eastern Time). If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Andrew Bee can be reached on 571-270-5183. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/GUILLERMO M RIVERA-MARTINEZ/ Primary Examiner, Art Unit 2677
Prosecution Insights