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 .
Status of Claims
Claims 1-20 are pending in this application.
Rejection under 35 U.S.C. §102
Applicant’s arguments, see page 8, line 8 through page 9, line 9, and the amendment to the claims, filed 27 January 2026, with respect to the rejection of claims 1, 6-9, 11 and 16-19 under 35 U.S.C. 102(a)(1) as being anticipated by Choi et al. (U.S. Patent Application Publication No. US 2023/0103966A1), have been fully considered but are not persuasive.
Applicant argues on page 8, line 8 through page 9, line 9 “Applicant has amended independent claims 1 and 11 to include the limitations of dependent claims 10 and 20, respectively, and has placed the original limitations of independent claims 1 and 11 in dependent claims 2 and 12, respectively ... Applicant respectfully submits that at least based on the Office Action's statement, page 9 of the Office Action, that original dependent claims 10 and 20 "would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims," Currently amended independent claims 1 and 11 should be in condition for allowance. Further, claims 6-9 and 16-19 depend from currently amended independent claims 1 and 11, respectively, and should also be allowed at least for the same reasons discussed above”, the examiner respectfully disagrees because applicant has not “rewritten in independent form including all of the limitations of the base claim and any intervening claims”, but rather presented new independent claims that do not include all of the limitations of the intervening claim nor all the limitations of the base claim. The new independent claims change the scope of the claim invention and necessitate new ground(s) of rejection which are presented hereinbelow.
Rejection under 35 U.S.C. §103
Applicant’s arguments, see page 9, line 10 through line 15, and the amendment to the claims, filed 27 January 2026, with respect to the rejection of claims 2-5 and 12-15 under 35 U.S.C. $103(a) as being unpatentable over Choi et al. (U.S. Patent Application Publication No. US2023/0103966 A1) in view of Luo et al. (U.S. Patent Application Publication No. US2021/0390375 A1), have been fully considered but are not persuasive.
Applicant argues on page 9, line 10 through line 15 “Applicant respectfully submits that claims 2-5 and 12-15 depend from currently amended independent claims 1 and 11, respectively, and should be allowed at least for the same reasons discussed above”, the examiner respectfully disagrees because applicant has not “rewritten in independent form including all of the limitations of the base claim and any intervening claims”, but rather presented new independent claims that do not include all of the limitations of the intervening claim nor all the limitations of the base claim. The new independent claims change the scope of the claim invention and necessitate new ground(s) of rejection which are presented hereinbelow.
Claim Rejections - 35 USC § 102
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 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 the appropriate paragraphs of 35 U.S.C. §102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-2, 6-9, 11-12 and 16-19 are rejected under 35 U.S.C. §102(a)(1) as being anticipated by Choi et al. (U.S. Patent Application Publication No. US 2023/0103966 A1) (hereafter referred to as “Choi (‘966)”).
With regard to claim 1, Choi (‘966) describes a hardware processor (see Figure 15, element 1510 and refer for example to paragraph [0108]); a system memory storing a software code (see Figure 15, element 1520 and refer for example to paragraphs [0108] and [0109]); the hardware processor configured to execute the software code to train a machine learning model using a discriminator to predict image noise by providing a test input to the discriminator, the test input being one of a test clean image, a test synthesized noise map generated by the machine learning model based on the test clean image and at least one test noise setting of a test camera used to capture a noisy version of the test clean image, and the at least one test noise setting, or the test clean image, a real noise map derived from the noisy version of the test clean image, and the at least one test noise setting, and determining, using the discriminator, whether the test input includes the real noise map or the test synthesized noise map (refer for example to paragraphs [0021], [0067], [0082] , [0097], [0098], [0102], [0110], [0111], [0112] and [0116] , the phrase “the test input being one of” was read disjunctively and the cited paragraphs describe the training of the machine learning model using a test input which includes the test clean image, a real noise map derived from the noisy version of the test clean image, and the at least one test noise setting).
As to claim 2, Choi (‘966) describes the system is configured to receive a clean image and at least one noise setting of a camera used to capture a version of the clean image that includes noise (refer for example to paragraph [0067]); provide the clean image and the at least one noise setting as a noise generation input to the machine learning model (refer for example to paragraph [0067]); and generate, using the machine learning model and based on the noise generation input, a synthesized noise map for renoising the clean image (refer for example to paragraphs [0082] and [0083] discusses the noise maps, and refer for example to paragraphs [0098], [0099] and [0102] discusses adding the noise map to the clean image which corresponds to applicant’s “a synthesized noise map for renoising the clean image”).
In regard to claim 6, Choi (‘966) describes wherein the noise in the version of the clean image comprises at least one of digital camera noise or film grain noise (refer for example to paragraphs [0065] and [0066]).
With regard to claim 7, Choi (‘966) describes wherein the synthesized noise map is generated by the machine learning model in a raw Red-Green-Blue (raw-RGB) color space (refer for example to paragraph [0067]).
As to claim 8, Choi (‘966) describes wherein the synthesized noise map is generated by the machine learning model in a standard Red-Green-Blue (sRGB) color space (refer for example to paragraph [0067]).
In regard to claim 9, Choi (‘966) describes wherein the hardware processor is further configured to execute the software code to renoise, using the synthesized noise map, the clean image to produce a renoised image (refer to paragraphs [0098], [0099] and [0102] discusses adding the noise map to the clean image which corresponds to applicant’s “a synthesized noise map for renoising the clean image”).
With regard to claim 11, Choi (‘966) describes training a machine learning model using a discriminator to predict image noise by providing a test input to the discriminator, the test input being one of a test clean image, a test synthesized noise map generated by the machine learning model based on the test clean image and at least one test noise setting of a test camera used to capture a noisy version of the test clean image, and the at least one test noise setting, or the test clean image, a real noise map derived from the noisy version of the test clean image, and the at least one test noise setting, and determining, using the discriminator, whether the test input includes the real noise map or the test synthesized noise map (refer for example to paragraphs [0021], [0067], [0082] , [0097], [0098], [0102], [0110], [0111], [0112] and [0116] , the phrase “the test input being one of” was read disjunctively and the cited paragraphs describe the training of the machine learning model using a test input which includes the test clean image, a real noise map derived from the noisy version of the test clean image, and the at least one test noise setting).
As to claim 12, Choi (‘966) describes receiving a clean image and at least one noise setting of a camera used to capture a version of the clean image that includes noise (see Figure 1, element 120 and refer for example to paragraphs [0067]); providing, by the software code executed by the hardware processor (see Figure 15, elements 1510 and 1520 and refer for example to paragraphs [0108] and [0109]), the clean image and the at least one noise setting as a noise generation input to the machine learning model (see Figure 1, element 120 and refer for example to paragraph [0065]); and generating, by the software code executed by the hardware processor (see Figure 15, elements 1510 and 1520 and refer for example to paragraphs [0108] and [0109]), using the machine learning model and based on the noise generation input, a synthesized noise map for renoising the clean image (refer to paragraphs [0082] and [0083] discusses the noise maps, and refer to paragraphs [0098], [0099] and [0102] discusses adding the noise map to the clean image which corresponds to applicant’s “a synthesized noise map for renoising the clean image”).
With regard to claim 16, Choi (‘966) describes wherein the noise in the version of the clean image comprises at least one of digital camera noise or film grain noise (refer for example to paragraphs [0065] and [0066]).
As to claim 17, Choi (‘966) describes wherein generating the synthesized noise map is performed by the machine learning model in a raw Red-Green-Blue (raw-RGB) color space (refer for example to paragraph [0067]).
In regard to claim 18, Choi (‘966) describes wherein generating the synthesized noise map is performed by the machine learning model in a standard Red-Green-Blue (sRGB) color space (refer for example to paragraph [0067]).
With regard to claim 19, Choi (‘966) describes renoising, by the software code executed by the hardware processor and using the synthesized noise map, the clean image to produce a renoised image (refer to paragraphs [0098], [0099] and [0102] discusses adding the noise map to the clean image which corresponds to applicant’s “a synthesized noise map for renoising the clean image”).
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 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(a) 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 set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 3-5, 10, 13-15 and 20 are rejected under 35 U.S.C. §103(a) as being unpatentable over Choi et al. (U.S. Patent Application Publication No. US 2023/0103966 A1) in view of Luo et al. (U.S. Patent Application Publication No. US 2021/0390375 A1) (hereafter referred to as “Luo”).
The arguments advanced in section 7 above, as to the applicability of Choi (‘966), are incorporated herein.
In regard to claims 3 and 13, Choi (‘966) describes using machine learning model, but does not expressly describe that the machine learning model comprises a generative convolutional neural network, such a technique is well known and widely utilized in the prior art.
Luo discloses a multi-sensor synthetic image fusion engine for mobile imaging system which uses a machine learning model (see Figure 2 and refer for example to paragraphs [0048] through [0050]) which provides for receiving a clean image and at least one noise setting of a camera used to capture a version of the clean image that includes noise, provides the clean image and the at least one noise setting as a noise generation input to the machine learning model and generates, using the machine learning model and based on the noise generation input, a synthesized noise map for renoising the clean image (refer for example to paragraphs [0059] and [0061]), and describes that the machine learning model comprises a generative convolutional neural network (see Figure 2, element and refer for example to paragraphs [0047] and [0048]).
Given the teachings of the two references and the same environment of operation, namely that of systems that receiving a clean image and at least one noise setting of a camera used to capture a version of the clean image that includes noise, provides the clean image and the at least one noise setting as a noise generation input to the machine learning model and generates, using the machine learning model and based on the noise generation input, a synthesized noise map for renoising the clean image, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Choi (‘966) system in the manner described by Luo according to known methods to yield predictable results and would have been motivated to do so with a reasonable expectation of success in order to provide for increased processing efficiency and higher accuracy as suggested by Luo (refer for example to paragraph [0004]), which fails to patentably distinguish over the prior art absent some novel and unexpected result.
With regard to claim 4, Luo describes wherein the machine learning model includes a plurality of encoder blocks and a plurality of decoder blocks, each of the plurality of encoder blocks and each of the plurality of decoder blocks including a respective plurality of simplified Nonlinear Activation Free blocks (see Figure 2, element and refer for example to paragraphs [0047] and [0048], Luo’s CNN inherently has encoder blocks and a plurality of decoder blocks).
As to claim 5, Luo describes wherein a noise output of each of the plurality of encoder blocks is injected into a respective one of the plurality of decoder blocks (see Figure 2, element and refer for example to paragraphs [0047] and [0048], Luo’s CNN inherently has encoder blocks and a plurality of decoder blocks).
With regard to claim 10, Luo describes wherein the machine learning model comprises a generative convolutional neural network and wherein each level of the generative convolutional neural network CNN has a same resolution (see Figure 2, element and refer for example to paragraphs [0047] and [0048]).
As to claim 14, Luo describes wherein the machine learning model includes a plurality of encoder blocks and a plurality of decoder blocks, each of the plurality of encoder blocks and each of the plurality of decoder blocks including a respective plurality of simplified Nonlinear Activation Free blocks (see Figure 2, element and refer for example to paragraphs [0047] and [0048], Luo’s CNN inherently has encoder blocks and a plurality of decoder blocks).
In regard to claim 15, Choi describes wherein a noise output of each of the plurality of encoder blocks is injected into a respective one of the plurality of decoder blocks (see Figure 2, element and refer for example to paragraphs [0047] and [0048], Luo’s CNN inherently has encoder blocks and a plurality of decoder blocks).
With regard to claim 20, Luo describes wherein the machine learning model comprises a generative convolutional neural network and wherein each level of the generative convolutional neural network CNN has a same resolution (see Figure 2, element and refer for example to paragraphs [0047] and [0048]).
Relevant Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Rowell, Choi, Tohme and Park all disclose systems similar to applicant’s claimed invention.
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 date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Jose L. Couso whose telephone number is (571) 272-7388. The examiner can normally be reached on Monday through Friday from 5:30am to 1:30pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Matthew Bella, can be reached on 571-272-7778. 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 Center information webpage on the USPTO website. For more information about the Patent Center, see https://www.uspto.gov/patents/apply/patent-center. Should you have questions about access to the Patent Center, contact the Patent Electronic Business Center (EBC) at 571-272-4100 or via email at: ebc@uspto.gov .
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.
/JOSE L COUSO/Primary Examiner, Art Unit 2667
January 30, 2026
Prosecution Insights