DETAILED ACTION
Applicant has amended claims 1, 9, 13, and 16. Claim 4 has been canceled. Claims 17-20 are new. Claims 1-3 and 5-20 are pending.
Response to Arguments
Applicant’s arguments filed on April 2, 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.
Regarding objection to specification under 35 U.S.C. 132(a) raised by amendment filed on December 11, 2025 introducing new matter into the disclosure, Applicant asserts that “the title "Distortion-Based Selection of Neural Network for Image and Video Coding" is supported by paragraphs [0100]-[0103] of the Published Specification, as well as by paragraphs [0014]-[0015], [0099], and [0144] of the Published Specification (Remarks, Pg. 7-8).
Applicant’s remarks above are acknowledged. However, the examiner was not able to find support for the title "Distortion-Based Selection of Neural Network for Image and Video Coding" in above cited paragraphs, as originally filed. There is no recitation anywhere in the specification, as originally filed, of selecting a neural network.
Therefore, based on above, Applicant’s remarks above are respectfully found unconvincing and prior objection(s) to specification under 35 U.S.C. 132(a) previously set forth in the last Office action (OA) are hereby maintained, as indicated below.
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 “selecting, based on the one or more determined parameters, a neural network… generating a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in lines 5-14 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 9 now recites the limitation “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in lines 15-18 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 13 now recites the limitation “select, based on the one or more determined parameters, a neural network… generate a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in lines 6-15 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
Claim 16 now recites the limitation “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in lines 13-18 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
New claim 19 recites the limitation “wherein the selecting, based on the one or more determined parameters, the neural network comprises: selecting the selected neural network from a plurality of pre-trained neural networks” in lines 1-3 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
New claim 20 recites the limitation “wherein the plurality of pre-trained neural networks comprises a plurality of neural networks trained for a plurality of compression levels” in lines 1-3 of the claim. The aforementioned claimed subject matter has no antecedent basis the specification, as originally filed.
The amendment filed on December 11, 2025 remains objected to under 35 U.S.C. 132(a) because it introduced new matter into the disclosure. 35 U.S.C. 132(a) states that no amendment shall introduce new matter into the disclosure of the invention. The added material which is not supported by the original disclosure is as follows: The Title of the invention was amended to recite “DISTORTION-BASED SELECTION OF NEURAL NETWORK FOR IMAGE AND VIDEO CODING”, as indicated in Pg. 2 of the amendment filed on December 11, 2025. However, the Title “DISTORTION-BASED SELECTION OF NEURAL NETWORK FOR IMAGE AND VIDEO CODING” has no antecedent bases in the originally filed specification of this application, as indicated in claims 1 and 13 above.
Applicant is required to cancel the new matter in the reply to this OA.
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 1-20 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 “selecting, based on the one or more determined parameters, a neural network… generating a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in lines 5-14 of the claim.
Applicant asserts that “with respect to claims 1 and 13, the Specification provides, at paragraphs [0100]-[0103] of the Published Specification (i.e., US 2023/0076920), nomenclature from which the terminology of the claims follows ” (Remarks, Pg. 7).
However, the examiner was not able to find support for the claimed feature limitations “selecting, based on the one or more determined parameters, a neural network… generating a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in the original disclosure.
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-202] of the specification also indicate “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network… during learning, the parameters of the network are adapted… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… In general, the less an image is compressed, the better the image quality of the compressed image. Since different compression levels introduce different compression artifacts, instead of training a single CNN to deal with all different compression levels, a specific CNN may be trained for each compression level… select a partitioning for a current block prediction mode… determine or select the best or an optimum prediction mode from a set of (e.g. pre-determined) prediction modes. The set of prediction modes may comprise, e.g., intra-prediction modes and/or inter-prediction modes… encoder 20 may, e.g., be configured to select a reference block from a plurality of reference blocks”.
However, the examiner was not able to find support for the claimed feature limitations “selecting, based on the one or more determined parameters, a neural network… generating a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in the disclosure, as originally filed.
Claims 2-3, 5-8, 12, and 17-20 are rejected by virtue of being dependent upon rejected base claim 1.
Claim 9 now recites the limitation “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in lines 15-18 of the claim.
Applicant asserts that “[w]ith respect to claims 9 and 16, it is respectfully submitted that support for the claimed subject matter identified in the Office Action is provided at paragraphs [0074]-[0075], [0080]-[0082], [0089], and [0130]-[0137]” (Remarks, Pg. 8).
However, the examiner was not able to find support for the claimed feature limitations “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in the original disclosure.
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-67] of the specification also indicates “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image”.
However, the examiner was not able to find support for the claimed feature limitations “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in the disclosure, as originally filed.
Claims 10-11 are rejected by virtue of being dependent upon rejected base claim 9.
Claim 13 now recites the limitation “select, based on the one or more determined parameters, a neural network… generate a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in lines 6-15 of the claim.
Applicant asserts that “with respect to claims 1 and 13, the Specification provides, at paragraphs [0100]-[0103] of the Published Specification (i.e., US 2023/0076920), nomenclature from which the terminology of the claims follows ” (Remarks, Pg. 7).
However, the examiner was not able to find support for the claimed feature limitations “select, based on the one or more determined parameters, a neural network… generate a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in the original disclosure.
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-202] of the specification also indicate “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network… during learning, the parameters of the network are adapted… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… In general, the less an image is compressed, the better the image quality of the compressed image. Since different compression levels introduce different compression artifacts, instead of training a single CNN to deal with all different compression levels, a specific CNN may be trained for each compression level… select a partitioning for a current block prediction mode… determine or select the best or an optimum prediction mode from a set of (e.g. pre-determined) prediction modes. The set of prediction modes may comprise, e.g., intra-prediction modes and/or inter-prediction modes… encoder 20 may, e.g., be configured to select a reference block from a plurality of reference blocks”.
However, examiner was not able to find support for the claimed feature limitations “select, based on the one or more determined parameters, a neural network… generate a correction image by processing the input image with the selected neural network… perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image, and at least one image up-sampling stage to perform up-sampling on a third intermediate representation corresponding to the input image” in the disclosure, as originally filed.
Claims 14-15 are rejected by virtue of being dependent upon rejected base claim 13.
Claim 16 now recites the limitation “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in lines 13-18 of the claim.
Applicant asserts that “[w]ith respect to claims 9 and 16, it is respectfully submitted that support for the claimed subject matter identified in the Office Action is provided at paragraphs [0074]-[0075], [0080]-[0082], [0089], and [0130]-[0137]” (Remarks, Pg. 8).
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-67] of the specification also indicates “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image”.
However, the examiner was not able to find support for the claimed feature limitations “perform down-sampling on the input training image or an intermediate representation corresponding to the input training image… perform filtering on a second intermediate representation corresponding to the input training image… perform up-sampling on a third intermediate representation corresponding to the input training image” in the disclosure, as originally filed.
Claim 19 recites the limitation “wherein the selecting, based on the one or more determined parameters, the neural network comprises: selecting the selected neural network from a plurality of pre-trained neural networks” in lines 1-3 of the claim.
Applicant asserts that “[s]upport for the new claims can be found, for example, in paragraphs [0100]-[0103] of the published specification” (Remarks, Pg. 8).
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-202] of the specification also indicate “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network… during learning, the parameters of the network are adapted… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… In general, the less an image is compressed, the better the image quality of the compressed image. Since different compression levels introduce different compression artifacts, instead of training a single CNN to deal with all different compression levels, a specific CNN may be trained for each compression level… select a partitioning for a current block prediction mode… determine or select the best or an optimum prediction mode from a set of (e.g. pre-determined) prediction modes. The set of prediction modes may comprise, e.g., intra-prediction modes and/or inter-prediction modes… encoder 20 may, e.g., be configured to select a reference block from a plurality of reference blocks”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the selecting, based on the one or more determined parameters, the neural network comprises: selecting the selected neural network from a plurality of pre-trained neural networks” in the disclosure, as originally filed.
Claim 20 is rejected by virtue of being dependent upon rejected claim 19.
Claim 20 recites the limitation “wherein the plurality of pre-trained neural networks comprises a plurality of neural networks trained for a plurality of compression levels” in lines 1-3 of the claim.
Applicant asserts that “[s]upport for the new claims can be found, for example, in paragraphs [0100]-[0103] of the published specification” (Remarks, Pg. 8).
Par. [0008-15] of the specification of this application indicate “generating a correction image by processing the input image with a neural network… the neural network is based on a U-net. For establishing the neural network, the U-net is modified… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… Parametrizing the neural network with a type of distortion or an amount of distortion may help to train the network”. Par. [0059-202] of the specification also indicate “using spatial (intra picture) prediction and/or temporal (inter picture) prediction to generate a prediction block… generate identical predictions (e.g. intra- and inter predictions) and/or re-constructions for processing… generating a correction image by processing the input image with a neural network… during learning, the parameters of the network are adapted… generating a correction image by processing the input image with a neural network, wherein the processing with the neural network includes at least one stage including image down-sampling and filtering of the down-sampled image. At least one stage of image up-sampling, and modifying the input image by combining the input image with the correction image… the neural network is parametrized according to a value of a parameter indicative of an amount or type of distortion of the input image… In general, the less an image is compressed, the better the image quality of the compressed image. Since different compression levels introduce different compression artifacts, instead of training a single CNN to deal with all different compression levels, a specific CNN may be trained for each compression level… select a partitioning for a current block prediction mode… determine or select the best or an optimum prediction mode from a set of (e.g. pre-determined) prediction modes. The set of prediction modes may comprise, e.g., intra-prediction modes and/or inter-prediction modes… encoder 20 may, e.g., be configured to select a reference block from a plurality of reference blocks”.
However, the examiner was not able to find support for the claimed feature limitations “wherein the plurality of pre-trained neural networks comprises a plurality of neural networks trained for a plurality of compression levels” 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 1-3 and 5-20 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 “perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image… perform up-sampling on a third intermediate representation corresponding to the input image” in lines 10-14 of the claim.
However, it is not clear what each of the claimed “intermediate representation corresponding to the input image”, “second intermediate representation corresponding to the input image”, and “third intermediate representation corresponding to the input image” in lines 10-14 of the claim, corresponds to, respectively, because the claimed “intermediate representation” term is not defined in the claims, or anywhere else in the specification, as indicated above. Additionally, it should be noted that the claimed “filtering” being performed recited in lines 11-12 of the claimed is not defined by the claims.
Therefore, based on above, 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 2-3, 5-8, 12, and 17-20 are rejected by virtue of being dependent upon rejected base claim 1.
Claim 9 now recites the limitation “perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image… perform up-sampling on a third intermediate representation corresponding to the input image” in lines 13-18 of the claim.
However, it is not clear what each of the claimed “intermediate representation corresponding to the input image”, “second intermediate representation corresponding to the input image”, and “third intermediate representation corresponding to the input image” in lines 13-18 of the claim, corresponds to, respectively, because the claimed “intermediate representation” term is not defined in the claims, or anywhere else in the specification, as indicated above. Additionally, it should be noted that the claimed “filtering” being performed recited in lines 15-16 of the claimed is not defined by the claims.
Therefore, based on above, 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 10-11 are rejected by virtue of being dependent upon rejected base claim 9.
Claim 13 now recites the limitation “perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image… perform up-sampling on a third intermediate representation corresponding to the input image” in lines 11-15 of the claim.
However, it is not clear what each of the claimed “intermediate representation corresponding to the input image”, “second intermediate representation corresponding to the input image”, and “third intermediate representation corresponding to the input image” in lines 11-15 of the claim, corresponds to, respectively, because the claimed “intermediate representation” term is not defined in the claims, or anywhere else in the specification, as indicated above. Additionally, it should be noted that the claimed “filtering” being performed recited in lines 13-14 of the claimed is not defined by the claims.
Therefore, based on above, 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 14-15 are rejected by virtue of being dependent upon rejected base claim 13.
Claim 16 now recites the limitation “perform down-sampling on the input image or an intermediate representation corresponding to the input image, at least one filter stage to perform filtering on a second intermediate representation corresponding to the input image… perform up-sampling on a third intermediate representation corresponding to the input image” in lines 13-18 of the claim.
However, it is not clear what each of the claimed “intermediate representation corresponding to the input image”, “second intermediate representation corresponding to the input image”, and “third intermediate representation corresponding to the input image” in lines 13-18 of the claim, corresponds to, respectively, because the claimed “intermediate representation” term is not defined in the claims, or anywhere else in the specification, as indicated above. Additionally, it should be noted that the claimed “filtering” being performed recited in lines 15-16 of the claimed is not defined by the claims.
Therefore, based on above, 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
The prior art made of record cited in PTO-892 and not relied upon is considered pertinent to applicant’s disclosure. In particular, US 2019/0279383 A1 (Angelova et al.) in Par. [0044-48] discloses “image depth recurrent neural network 102 includes a down-sampling recurrent sub-neural network 202 followed by an up-sampling recurrent sub-network 204. The down-sampling recurrent sub-neural network 202 includes one or more convolutional LSTM neural network layers… Similarly, the up-sampling recurrent sub-neural network 204 includes one or more convolutional LSTM neural network layers … skip connections are added from the encoder to the decoder. A skip connection concatenates the output of a layer in the decoder to the inputs of its corresponding similarly sized layer in the decoder. Intermediate low-resolution predictions are performed… The intermediate predictions are used in the loss function as well”, for example, and US 2018/0150947 A1 (Lu et al.) in Par. [0003-4] discloses “system can be comprised of multiple neural networks…Training of such a neural network system can be accomplished using an image neural network and a painting neural network. First, the image neural network is trained by inputting a training sketch into the image neural network to generate a training intermediate image… Differences between the training intermediate image and a reference image are used to determined errors in the image neural network. The reference image is what the intermediate image should look like if the neural network was functioning perfectly. In other words, the reference image is a ground-truth image that the network compares itself to in order to determine errors. Such errors can be used to improve the image neural network by backwards propagation of the errors through the network”, and in Par. [0055-69] discloses “image neural network transforms the training sketch into a training intermediate image. This can be accomplished, for example, by downsampling the training sketch to a lower dimension, performing a sequence of non-linear transformations using a number of filters to generate the training intermediate image, and then upsampling the training intermediate image to the desired output size… To train the image neural network, an intermediate image can be generated using the image neural network based on an input sketch generated from a reference image… An intermediate image generally refers to an image generated via the image neural network. Intermediate images generated in accordance with training the image neural network may be referred to herein as training images or training intermediate images. The generated intermediate image can be compared to a reference image to facilitate training of the image neural network. In this regard, the image neural network can be modified or adjusted based on the comparison such that the quality of subsequently generated intermediate images increases”, respectively, for example, appear to teach a similar concept related to original claims including the now claimed “intermediate representation”.
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