CTNF 18/810,874 CTNF 81428 DETAILED ACTION Notice of Pre-AIA or AIA Status 07-03-aia AIA 15-10-aia The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA. Information Disclosure Statement The information disclosure statement (IDS) submitted on 29 April 2026 is being considered by the examiner. Claim Rejections - 35 USC § 103 07-06 AIA 15-10-15 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. 07-20-aia AIA 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. 07-23-aia AIA 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. 07-21-aia AIA Claim s 1-3 are rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) . Regarding claim 1 , Chemerys et al. disclose a computer-implemented method (Figure 4) of image-to-image translation that, when executed by data processing hardware, causes the data processing hardware to perform operations comprising: applying a technique to an input image to generate a source-domain seed (Figure 4, input image 402 has a technique applied to generate a source-domain seed, i.e. the noise data introduced at 406-408, see paragraph [0125], for example, generates a source-domain seed at 410.); translating the source-domain seed to a target-domain seed using a translation module (Figure 4, 410 and 414 and paragraph [0136], UNet is used for translation.); and sampling the target-domain seed to generate a denoised code (Figure 4, 434, iterative denoising 416 provides for sampling to generate a denoised code. See paragraph [0129].). Chemerys et al. fail to teach of applying an inversion technique to the input image to generate the source-domain seed. Zhang et al. disclose of applying an inversion technique to an input image to generate a source-domain seed (Paragraph [0080] explains that latent noise space inversion is used to generate a noise representation.). Hence the prior art includes each element claimed although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of the actual combination of the elements in a single prior art reference. In combination Chemerys et al. performs the same function as it does separately of generating a noise representation, and Zhang et al. performs the same function as it does separately of using latent noise space inversion to generate a noise representation. Therefore, one of ordinary skill in the art before the effective filing date of the claimed invention could have combined the elements as claimed by known methods, and that in combination, each element merely performed the same function as it does separately. The results of the combination would have been predictable and resulted in applying an inversion technique to the input image to generate the source-domain seed. Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Regarding claim 2 , Chemerys et al. and Zhang et al. disclose the method of Claim 1, further comprising: encoding the input image to a latent space to generate an encoded input image (Chemerys et al.: Figure 4, 404 is an encoder.); and decoding the denoised code to generate a translated image (Chemerys et al.: Figure 4, 418 is a decoder.). Regarding claim 3 , Chemerys et al. and Zhang et al. disclose the method of Claim 2, wherein encoding the input image further comprises applying a stable diffusion model to the input image (Chemerys et al.: Paragraph [0117].) . 07-21-aia AIA Claim s 4 and 7 are rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) and further in view of Li et al. (US 2024/0296607) . Regarding claim 4 , Chemerys et al. and Zhang et al. disclose the method of Claim 2. Chemerys et al. and Zhang et al. fail to teach wherein applying the inversion technique to the encoded input image to generate the source-domain seed further includes applying a denoising diffusion implicit model (DDIM) inversion to the encoded input image. Li et al. disclose wherein applying an inversion technique to the encoded input image to generate the source-domain seed further includes applying a denoising diffusion implicit model (DDIM) inversion to the encoded input image (Figure 9, 908 and 910 and paragraphs [0055] and [0107].). Hence the prior art includes each element claimed although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of the actual combination of the elements in a single prior art reference. In combination, the combination of Chemerys et al. and Zhang et al. performs the same function as it does separately of applying an inversion technique, and Li et al. performs the same function as it does separately of applying a denoising diffusion implicit model (DDIM) inversion to the encoded input image. Therefore, one of ordinary skill in the art before the effective filing date of the claimed invention could have combined the elements as claimed by known methods, and that in combination, each element merely performed the same function as it does separately. The results of the combination would have been predictable and resulted in applying the inversion technique to the encoded input image to generate the source-domain seed further including applying a denoising diffusion implicit model (DDIM) inversion to the encoded input image. Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention. Regarding claim 7 , Chemerys et al. and Zhang et al. disclose the method of Claim 1. Chemerys et al. and Zhang et al. fail to teach wherein translating the source-domain seed includes applying a seed-to-seed generative adversarial network (sts-GAN). Li et al. disclose translating the source-domain seed includes applying a seed-to-seed generative adversarial network (Paragraphs [0035]-[0036] and [0106].). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the generative adversarial network teachings of Li et al. for the translating in the method taught by the combination of Chemerys et al. and Zhang et al. The motivation to combine would have been in order to make use of the known benefits of GANs, such as superior image sharpness and faster inference times . 07-21-aia AIA Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) and further in view of Zhou et al. (WO 2020/215369 A1) . Regarding claim 5 , Chemerys et al. and Zhang et al. disclose the method of Claim 2. Chemerys et al. and Zhang et al. fail to teach wherein decoding the denoised code further includes generating code of the translated image that includes a global appearance effect or removes a global appearance effect. Zhou et al. disclose wherein decoding a denoised code includes generating code of the translated image that includes a global appearance effect or removes a global appearance effect (See page 49 of the provided document, second to last paragraph, which recites “According to a preferred embodiment of the present disclosure, it is also possible to determine rain, snow, and fog weather based on some of the aforementioned parameters, and trigger the activation of the denoising unit 302. For example, when the reflectivity of the point in the point cloud is higher than a certain threshold, it can be determined that it is snowy, and the denoising unit 302 can be triggered to turn on at this time. In addition, when the number of echo pulses of a point in the point cloud exceeds a certain threshold, it can be determined as a foggy day, and at this time, the denoising unit 302 can be triggered to turn on.” Where below threshold the global appearance is included, i.e. not removed, and when it is above the threshold the global appearance is removed.). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the global appearance teachings of Zhou et al. in the method taught by the combination of Chemerys et al. and Zhang et al. The motivation to combine would have been in order to provide clearer, better visibility images . 07-21-aia AIA Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) and further in view of Fu et al. (US 2019/0295302) . Regarding claim 6 , Chemerys et al. and Zhang et al. disclose the method of Claim 2. Chemerys et al. and Zhang et al. fail to teach the method further comprising applying a spatial guidance module to maintain structural similarity between the input image and the translated image. Fu et al. disclose a method comprising applying a spatial guidance module to maintain structural similarity between the input image and the translated image (Paragraph [0044]). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the spatial guidance module teachings of Fu et al. in the method taught by the combination of Chemerys et al. and Zhang et al. The motivation to combine would have been in order to maintain structural similarity between the input image and the translated image . 07-21-aia AIA Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) and further in view of Zhang et al. (US 2023/0298148) . Regarding claim 8 , Chemerys et al. and Zhang et al. (US 2025/0046055) disclose the method of Claim 1. Chemerys et al. and Zhang et al. fail to teach wherein sampling the target-domain seed further comprises preserving semantic and structure details of the input image. Zhang et al. (US 2023/0298148) disclose wherein sampling a target-domain seed further comprises preserving semantic and structure details of the input image (Paragraph [0017]). Hence the prior art includes each element claimed although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of the actual combination of the elements in a single prior art reference. In combination, the combination of Chemerys et al. and Zhang et al. (US 2025/0046055) performs the same function as it does separately of sampling a target-domain seed, and Zhang et al. (US 2023/0298148) performs the same function as it does separately of preserving semantic and structure details of the input image. Therefore, one of ordinary skill in the art before the effective filing date of the claimed invention could have combined the elements as claimed by known methods, and that in combination, each element merely performed the same function as it does separately. The results of the combination would have been predictable and resulted in the sampling preserving semantic and structure details of the input image. Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention . 07-21-aia AIA Claim s 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Chemerys et al. (US 2024/0395028) in view of Zhang et al. (US 2025/0046055) and further in view of Liu (CN 117853865 A) . Regarding claim 9 , Chemerys et al. and Zhang et al. disclose the method of Claim 1. Chemerys et al. and Zhang et al. fail to teach wherein wherein sampling the target-domain seed further comprises applying a pre-trained stable diffusion model with a target output prompt. Liu discloses wherein sampling a target-domain seed comprises applying a pre-trained stable diffusion model with a target output prompt (See page 22 of the provided document, last paragraph: “In the embodiment of the invention, the LoRA fine adjustment model (Low-Rank of Large Language Models, low-rank adaptation of large language model)…and the pre-training stable diffusion model (Diffuison) is a diffusion model from text to image, which can realize generating the picture related to the prompt through the character/picture prompt. Its working principle is to "destroy" training data by iteratively adding Gaussian noise, then learn how to eliminate noise to recover data, use FrozenCLIPEmbedder text encoder to encode prompt word, generate embedded representation of text. U-Net receives the potential representation of the image and the embedded representation of the text at the same time, and uses the attention mechanism to better learn the matching relationship between the text and the image.”). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the pre-trained stable diffusion model teachings of Liu in the sampling in the method taught by the combination of Chemerys et al. and Zhang et al. The motivation to combine would have been in order to make use of the known benefits of pre-trained stable diffusion models, such as eliminating the need to train the AI system from scratch, thus saving time and cost. Regarding claim 10 , Chemerys et al., Zhang et al. and Liu disclose the method of Claim 9, wherein applying the pre-trained stable diffusion model further comprises identifying a relationship between the source-domain seed and the target-domain seed (Liu: page 22 of the provided document, last paragraph.) . 07-21-aia AIA Claim s 11-14 are rejected under 35 U.S.C. 103 as being unpatentable over in Li et al. (US 2024/0296607) view of Chemerys et al. (US 2024/0395028) . Regarding claim 11 , Li et al. disclose a system (Figure 18) for image-to-image translation in a diffusion seed space for generating perception data for a perception system of a vehicle [intended use in preamble], comprising: data processing hardware (Figure 18, 1802); and memory hardware in communication with the data processing hardware (Figure 18, 1804 and 1806), the memory hardware storing instructions that, when executed on the data processing hardware, cause the data processing hardware to perform operations (Paragraph [0170]) comprising: encoding an input image to a stable diffusion latent space to generate an encoded input image (Figure 9, 904 and paragraph [0106].); applying a denoising diffusion implicit model (DDIM) inversion to the encoded input image to generate a source-domain seed (Figure 9, 908 and 910 and paragraphs [0055] and [0107].); sampling the source-domain seed to generate a denoised code (Figure 9, the sampling at 312a-914a-312b-914b-312n is used to generate a denoised code at 916. See paragraph [0109].); and decoding the denoised code to generate a translated image (Figure 9, 918 and paragraph [0110].). Li et al. fail to explicitly teach of translating the source-domain seed to a target-domain seed using a translation module. Chemerys et al. disclose of translating a source-domain seed to a target-domain seed using a translation module in a diffusion model (Figure 4, 410 and 414 and paragraph [0136], UNet is used for translation.). Thus, Li et al. and Chemerys et al. each disclose a denoising structure. A person of ordinary skill in the art before the effective filing date of the claimed invention would have recognized that the iterative denoising structure of Chemerys et al. could have been substituted for the denoising structure of Li et al. because both provide a denoising function. Furthermore, a person of ordinary skill in the art would have been able to carry out the substitution. Finally, the substitution achieves the predictable result of providing denoising. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to substitute the iterative denoising structure of Chemerys et al. for the denoising structure of Li et al. according to known methods to yield the predictable result of providing denoising. Regarding claim 12 , Li et al. and Chemerys et al. disclose the system of Claim 11, wherein encoding the input image further comprises applying a stable diffusion model to the input image (Chemerys et al.: Paragraph [0117].). Regarding claim 13 , Li et al. and Chemerys et al. disclose the system of Claim 11, wherein applying the denoising diffusion implicit model inversion to the input image further comprises receiving a source input prompt (Li et al.: Figure 3 and paragraph [0055]). Regarding claim 14 , Li et al. and Chemerys et al. disclose the system of Claim 11, wherein translating the source-domain seed includes applying a seed-to-seed generative adversarial network (sts-GAN) (Li et al.: Paragraphs [0035]-[0036] and [0106].) . 07-21-aia AIA Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over in Li et al. (US 2024/0296607) view of Chemerys et al. (US 2024/0395028) and further in view of Zhang et al. (US 2023/0298148) . Regarding claim 15 , Li et al. and Chemerys et al. disclose the system of Claim 11. Li et al. and Chemerys et al. fail to teach wherein sampling the target-domain seed further comprises preserving semantic and structure details of the input image. Zhang et al. disclose wherein sampling a target-domain seed further comprises preserving semantic and structure details of the input image (Paragraph [0017]). Hence the prior art includes each element claimed although not necessarily in a single prior art reference, with the only difference between the claimed invention and the prior art being the lack of the actual combination of the elements in a single prior art reference. In combination, the combination of Li et al. and Chemerys et al. performs the same function as it does separately of sampling a target-domain seed, and Zhang et al. performs the same function as it does separately of preserving semantic and structure details of the input image. Therefore, one of ordinary skill in the art before the effective filing date of the claimed invention could have combined the elements as claimed by known methods, and that in combination, each element merely performed the same function as it does separately. The results of the combination would have been predictable and resulted in the sampling preserving semantic and structure details of the input image. Therefore, the claimed subject matter would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention . 07-21-aia AIA Claim s 16-17 are rejected under 35 U.S.C. 103 as being unpatentable over in Li et al. (US 2024/0296607) view of Chemerys et al. (US 2024/0395028) and further in view of Liu (CN 117853865 A) . Regarding claim 16 , Li et al. and Chemerys et al. disclose the system of Claim 11. Li et al. and Chemerys et al. fail to teach wherein sampling the target-domain seed further comprises applying a pre-trained stable diffusion model with a target output prompt. Liu discloses wherein sampling a target-domain seed comprises applying a pre-trained stable diffusion model with a target output prompt (See page 22 of the provided document, last paragraph: “In the embodiment of the invention, the LoRA fine adjustment model (Low-Rank of Large Language Models, low-rank adaptation of large language model)…and the pre-training stable diffusion model (Diffuison) is a diffusion model from text to image, which can realize generating the picture related to the prompt through the character/picture prompt. Its working principle is to "destroy" training data by iteratively adding Gaussian noise, then learn how to eliminate noise to recover data, use FrozenCLIPEmbedder text encoder to encode prompt word, generate embedded representation of text. U-Net receives the potential representation of the image and the embedded representation of the text at the same time, and uses the attention mechanism to better learn the matching relationship between the text and the image.”). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the pre-trained stable diffusion model teachings of Liu in the sampling in the method taught by the combination of Li et al. and Chemerys et al. The motivation to combine would have been in order to make use of the known benefits of pre-trained stable diffusion models, such as eliminating the need to train the AI system from scratch, thus saving time and cost. Regarding claim 17 , Li et al., Chemerys et al. and Liu disclose the system of Claim 16, wherein applying the pre-trained stable diffusion model further comprises identifying a relationship between the source-domain seed and the target-domain seed (Liu: page 22 of the provided document, last paragraph.) . 07-21-aia AIA Claim s 18-19 are rejected under 35 U.S.C. 103 as being unpatentable over in Li et al. (US 2024/0296607) view of Chemerys et al. (US 2024/0395028) and further in view of Zhou et al. (WO 2020/215369 A1) . Regarding claim 18 , Li et al. and Chemerys et al. disclose the system of Claim 11. Li et al. and Chemerys et al. fail to teach wherein decoding the denoised code further includes generating code of the translated image that includes a global appearance effect. Zhou et al. disclose wherein decoding a denoised code includes generating code of the translated image that includes a global appearance effect (See page 49 of the provided document, second to last paragraph, which recites “According to a preferred embodiment of the present disclosure, it is also possible to determine rain, snow, and fog weather based on some of the aforementioned parameters, and trigger the activation of the denoising unit 302. For example, when the reflectivity of the point in the point cloud is higher than a certain threshold, it can be determined that it is snowy, and the denoising unit 302 can be triggered to turn on at this time. In addition, when the number of echo pulses of a point in the point cloud exceeds a certain threshold, it can be determined as a foggy day, and at this time, the denoising unit 302 can be triggered to turn on.” Where below threshold the global appearance is included, i.e. not removed, and when it is above the threshold the global appearance is removed.). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the global appearance teachings of Zhou et al. in the method taught by the combination of Chemerys et al. and Zhang et al. The motivation to combine would have been in order to provide clearer, better visibility images. Regarding claim 19 , Li et al., Chemerys et al. and Zhou et al. disclose the system of Claim 18, wherein decoding the denoised code further includes generating code of the translated image that removes a global appearance effect (Zhou et al.: See page 49 of the provided document, second to last paragraph, which recites “According to a preferred embodiment of the present disclosure, it is also possible to determine rain, snow, and fog weather based on some of the aforementioned parameters, and trigger the activation of the denoising unit 302. For example, when the reflectivity of the point in the point cloud is higher than a certain threshold, it can be determined that it is snowy, and the denoising unit 302 can be triggered to turn on at this time. In addition, when the number of echo pulses of a point in the point cloud exceeds a certain threshold, it can be determined as a foggy day, and at this time, the denoising unit 302 can be triggered to turn on.” Where below threshold the global appearance is included, i.e. not removed, and when it is above the threshold the global appearance is removed.) . 07-21-aia AIA Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over in Li et al. (US 2024/0296607) view of Chemerys et al. (US 2024/0395028) and further in view of Fu et al. (US 2019/0295302) . Regarding claim 20 , Li et al. and Chemerys et al. disclose the system of Claim 11. Li et al. and Chemerys et al. fail to teach the system further comprising applying a spatial guidance module to maintain structural similarity between the input image and the translated image. Fu et al. disclose a method comprising applying a spatial guidance module to maintain structural similarity between the input image and the translated image (Paragraph [0044]). Therefore, it would have been obvious to “one of ordinary skill” in the art before the effective filing date of the claimed invention to use the spatial guidance module teachings of Fu et al. in the system taught by the combination of Li et al. and Chemerys et al. The motivation to combine would have been in order to maintain structural similarity between the input image and the translated image. Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to STEPHEN G SHERMAN whose telephone number is (571)272-2941. The examiner can normally be reached Monday - Friday, 8:00am - 4pm ET. 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, AMR AWAD can be reached at (571)272-7764. 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. /STEPHEN G SHERMAN/Primary Examiner, Art Unit 2621 15 June 2026 Application/Control Number: 18/810,874 Page 2 Art Unit: 2621 Application/Control Number: 18/810,874 Page 3 Art Unit: 2621 Application/Control Number: 18/810,874 Page 4 Art Unit: 2621 Application/Control Number: 18/810,874 Page 5 Art Unit: 2621 Application/Control Number: 18/810,874 Page 6 Art Unit: 2621 Application/Control Number: 18/810,874 Page 7 Art Unit: 2621 Application/Control Number: 18/810,874 Page 8 Art Unit: 2621 Application/Control Number: 18/810,874 Page 9 Art Unit: 2621 Application/Control Number: 18/810,874 Page 10 Art Unit: 2621 Application/Control Number: 18/810,874 Page 11 Art Unit: 2621 Application/Control Number: 18/810,874 Page 12 Art Unit: 2621 Application/Control Number: 18/810,874 Page 13 Art Unit: 2621 Application/Control Number: 18/810,874 Page 14 Art Unit: 2621 Application/Control Number: 18/810,874 Page 15 Art Unit: 2621 Application/Control Number: 18/810,874 Page 16 Art Unit: 2621 Application/Control Number: 18/810,874 Page 17 Art Unit: 2621
Prosecution Insights