DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 12/05/2024 has been made of record and considered by the examiner.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they include the following reference character(s) not mentioned in the description: #1610 of FIG. 16, see [00149]. Corrected drawing sheets in compliance with 37 CFR 1.121(d), or amendment to the specification to add the reference character(s) in the description in compliance with 37 CFR 1.121(b) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Objections
Claims 2-4, 6-11, and 13-16 are objected to because of the following informalities: the claims repeatedly recite “for the obtaining” and “for the generating.” Many of these recitations are redundant, and therefore add ambiguity to the claims, and should be corrected to “to obtain” and “to generate,” or removed altogether. Appropriate correction is required.
Claim 19 is objected to because of the following informalities: the second limitation recites “generating a first transfer image,” however, claim 17, from which 19 depends, already discloses “generating a first transfer image.” The limitation should be corrected to “generating the first transfer image.” Appropriate correction is required.
Claim Rejections - 35 USC § 112
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 9 and 10 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.
A broad range or limitation together with a narrow range or limitation that falls within the broad range or limitation (in the same claim) may be considered indefinite if the resulting claim does not clearly set forth the metes and bounds of the patent protection desired. See MPEP § 2173.05(c). In the present instance, claim 9 recites the broad recitation “the one or more processors are configured to: adjust either one or both of the transfer quality evaluation data and the truth value data”, and the claim also recites “adjust the style transfer loss, based on the adjusted transfer quality evaluation data and the modified truth value data” which is the narrower statement of the range/limitation. The claim(s) are considered indefinite because there is a question or doubt as to whether the modified truth value data introduced by such narrower language is (a) merely exemplary of the remainder of the claim, and therefore not required, or (b) a required feature of the claims. Appropriate correction is required.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-8 and 12-19 are rejected under 35 U.S.C. 103 as being unpatentable over Chen (CN115439380B), in further view of Ansari (‘Refining Deep Generative Models Via Discriminator Gradient Flow’), and in further view of Li (‘GradNet: Gradient-Guided Network for Visual Object Tracking’).
Consider claims 1 and 17, Chen discloses an apparatus/processor-implemented method with image processing, the apparatus (¶5) comprising:
one or more processors configured to (¶5):
generate a first transfer image corresponding to an input image by performing style transfer on the input image, using an image style transformer model (¶40-45, 80-87; “S2. … the image of the input conditional generator unit in step S1 is encoded and conditionally decoded to output the synthesized image IS, so that the synthesized image IS has the style features represented by the conditional label c′ and the shape features of the input image.”; “condition generator unit 130 is used to encode and conditionally decode the image input to the condition generator unit 130 using a convolutional neural network and according to the input condition label”);
obtain transfer quality evaluation data on the first transfer image, using the image style transformer model (¶46-50, 87; “conditional discriminator unit 140 is used to perform conditional encoding on the synthesized image IS and the real image IR output by the conditional generator unit using a convolutional neural network and based on the input conditional labels. It outputs two discriminator feedback values that reflect the degree of authenticity of the synthesized image IS and the real image IR output by the conditional generator unit, respectively…”);
obtain a gradient for a style transfer loss, based on the transfer quality evaluation data (¶51-56, 87-88, “S4. Calculate the target loss function, calculate the gradient of the parameters in the conditional generator unit and the conditional discriminator unit based on the backpropagation of the loss function”);
obtain update information on the first transfer image from an update information generation model to which the gradient is input (¶51-56, 87-88, 120-126; “The model optimizer unit 150 is used to calculate the target loss function, calculate the gradient of the parameters in the condition generator unit 130 and the condition discriminator unit 140 according to the backpropagation of the loss function, adjust the gradient magnitude of the synthetic image IS output by the condition generator unit, and finally update the parameters of the condition generator unit 130 and the condition discriminator unit 140 according to the calculated parameter gradient.”).
Chen fails to explicitly disclose generate a second transfer image by updating the first transfer image, based on the update information.
In related art, Ansari discloses obtain update information on the first transfer image from an update information generation model to which the gradient is input (Ansari 3. Generator Refinement via Discriminator Gradient Flow; 3.1 Refinement in the Latent Space); and
generate a second transfer image by updating the first transfer image, based on the update information (Ansari 3. Generator Refinement via Discriminator Gradient Flow; 3.1 Refinement in the Latent Space; 3.2 Refinement for All).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the refinement vis discriminator gradient flow of Ansari into the style transfer processing of Chen to further optimize the output image and predictably yield the generation of a second latent variable (Chen ¶126-130; Ansari Section 3).
In related art, Li further discloses obtain update information on the first transfer image from an update information generation model to which the gradient is input (Li 3.2 Template Generation, Algorithm 1); and
generate a second transfer image by updating the first transfer image, based on the update information (Li 3.2 Template Generation, Algorithm 1).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the update technique of Li into the style transfer processing of Chen, as modified by Ansari, to further optimize the output image and predictably yield the generation of a second transfer image (Chen ¶126-130; Ansari Section 3; Li Section 3).
Consider claim 12, Chen discloses an apparatus with image processing, the apparatus comprising: one or more processors configured to:
generate a first transfer image corresponding to an input image by performing style transfer on the input image, using an image style transformer model (¶40-45, 80-87, 121-126; “S2. … the image of the input conditional generator unit in step S1 is encoded and conditionally decoded to output the synthesized image IS, so that the synthesized image IS has the style features represented by the conditional label c′ and the shape features of the input image.”);
obtain control data comprising image style transfer information (¶80-87, 124-130);
obtain a gradient for a style transfer loss, based on the control data (¶46-56, 80-87, 124-130).
Chen fails to explicitly disclose generate a second transfer image by updating the first transfer image, based on the gradient.
In related art, Ansari discloses obtain update information on the first transfer image from an update information generation model to which the gradient is input (Ansari 3. Generator Refinement via Discriminator Gradient Flow; 3.1 Refinement in the Latent Space); and
generate a second transfer image by updating the first transfer image, based on the gradient (Ansari 3. Generator Refinement via Discriminator Gradient Flow; 3.1 Refinement in the Latent Space; 3.2 Refinement for All).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the refinement vis discriminator gradient flow of Ansari into the style transfer processing of Chen to further optimize the output image and predictably yield the generation of a second latent variable (Chen ¶126-130; Ansari Section 3).
In related art, Li further discloses generate a second transfer image by updating the first transfer image, based on the gradient (Li 3.2 Template Generation, Algorithm 1.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the update technique of Li into the style transfer processing of Chen, as modified by Ansari, to further optimize the output image and predictably yield the generation of a second transfer image (Chen ¶126-130; Ansari Section 3; Li Section 3).
Consider claims 2 and 18, Chen, as modified by Ansari and Li, discloses the claimed invention wherein, for the obtaining of the gradient, the one or more processors are configured to:
obtain control data comprising image style transfer information (Chen ¶80-87, 124-126); and
obtain the gradient, based on the transfer quality evaluation data and the control data (Chen ¶46-56, 80-87, 124-130).
Consider claims 3 and 19, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the one or more processors are configured to:
obtain a first latent variable by encoding the input image, using the image style transformer model (Chen ¶41-50, 90-100);
for the generating of the first transfer image, generate the first transfer image by decoding the first latent variable, using the image style transformer model (Chen ¶41-50, 90-100);
obtaining a second latent variable by updating the first latent variable, based on the update information (Chen ¶122-126; Ansari Section 3, Algorithm 1; Li 3.2 Template Generation, Eq. 6); and
for the generating of the second transfer image, generate the second transfer image by decoding the second latent variable, using the image style transformer model (Chen ¶90-100, 122-130; Ansari Section 3, Algorithm 1, Li 3.2 Template Generation).
Consider claim 4, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the transfer quality evaluation data comprises reliability of the first transfer image for the input image (Chen ¶46, 85-90),
for the obtaining of the gradient, the one or more processors are configured to:
determine a style transfer loss, based on the transfer quality evaluation data and truth value data (Chen ¶46, 85-90, 120-130); and
obtain the gradient, based on the determined style transfer loss, and the truth value data comprises expected reliability for each pixel of the first transfer image (Chen ¶46, 85-90, 120-130; Li 3.2 Template Generation, Eq. 5; 3.4 Online Tracking, Algorithm 1).
Consider claim 5, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the control data comprises any one or any combination of any two or more of a direction of the style transfer, a degree of the style transfer, and a position of the style transfer (Chen ¶66-69, 124, 130).
Consider claim 6, Chen, as modified by Ansari and Li, discloses the claimed invention wherein, for the obtaining of the gradient, the one or more processors are configured to: obtain a first gradient, based on the transfer quality evaluation data (Chen ¶46-56, 80-87, 124-130);
obtain a second gradient, based on the control data (Chen ¶46-56, 80-87, 124-130); and
obtain the gradient by fusing the first gradient and the second gradient (Chen ¶46-56, 80-87, 124-130, 150-156).
Consider claim 7, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the transfer quality evaluation data comprises reliability data of the first transfer image for the input image, for the obtaining of the first gradient (Chen ¶46, 85-90), the one or more processors are configured to:
determine the style transfer loss, based on the transfer quality evaluation data and truth value data (Chen ¶46, 85-90, 120-130); and
obtain the first gradient based on the determined style transfer loss, and the truth value data comprises expected reliability data for each pixel of the first transfer image (Chen ¶46, 85-90, 120-130; Li 3.2 Template Generation, Eq. 5; 3.4 Online Tracking, Algorithm 1).
Consider claim 8, Chen, as modified by Ansari and Li, discloses the claimed invention wherein, for the obtaining of the second gradient, the one or more processors are configured to: adjust the style transfer loss, based on the control data (Chen ¶51-66; Ansari Section 3, Algorithm 1); and
obtain the second gradient, based on the adjusted style transfer loss (Ansari Section 3, Algorithm 1; Li Section 3, Algorithm 1).
Consider claim 13, Chen, as modified by Ansari and Li, discloses the claimed invention wherein, for the obtaining of the gradient, the one or more processors are configured to:
adjust the style transfer loss, based on the control data (Chen ¶46-56, 80-87, 124-130); and
obtain the gradient, based on the adjusted style transfer loss (Chen ¶46-56, 80-87, 124-130).
Consider claim 14, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the image style transformer model is a generative adversarial neural network, and for the obtaining of the gradient, the one or more processors are configured to: obtain transfer quality evaluation data of the first transfer image, using the generative adversarial neural network (Chen ¶46-66, 80-87, 124-130); and
obtain the gradient, based on the transfer quality evaluation data and the control data (Chen ¶46-56, 80-87, 124-130).
Consider claim 15, Chen, as modified by Ansari and Li, discloses the claimed invention wherein, for the generating of the second transfer image, the one or more processors are configured to: obtain update information on the first transfer image from an update information generation model to which the gradient is input (Chen ¶122-126; Ansari Section 3, Algorithm 1; Li 3.2 Template Generation, Eq. 6); and
generate the second transfer image by updating the first transfer image, based on the update information (Chen ¶90-100, 122-130; Ansari Section 3, Algorithm 1, Li 3.2 Template Generation).
Consider claim 16, Chen, as modified by Ansari and Li, discloses the claimed invention wherein the image style transformer model is a generative adversarial neural network, and the one or more processors are configured to: obtain a first latent variable by encoding the input image, using the image style transformer model (Chen ¶41-50, 90-100);
for the generating of the first transfer image, generate the first transfer image by decoding the first latent variable, using the image style transformer model (Chen ¶41-50, 90-100);
obtain a second latent variable by updating the first latent variable, based on the update information (Chen ¶122-126; Ansari Section 3, Algorithm 1; Li 3.2 Template Generation, Eq. 6); and
for the generating of the second transfer image, generate the second transfer image by decoding the second latent variable, using the image style transformer model (Chen ¶90-100, 122-130; Ansari Section 3, Algorithm 1, Li 3.2 Template Generation).
Allowable Subject Matter
Claims 9-11 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten (1) in independent form including all of the limitations of the base claim and any intervening claims, and (2) to overcome other currently applied rejections.
Relevant Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US 2021/0125061 A1 discloses a method for the generation of synthetic data in generative networks.
CN114385883A (from IDS) discloses a contour enhancement method used in style conversion.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ASHLEY HYTREK whose telephone number is (703)756-4562. The examiner can normally be reached M-F 9:00-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Steve Koziol can be reached at (408)918-7630. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ASHLEY HYTREK/Examiner, Art Unit 2665
/Stephen R Koziol/Supervisory Patent Examiner, Art Unit 2665
Prosecution Insights