CTNF 18/737,450 CTNF 87613 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. Prior arts cited in this office action: Li et al. (CN 114549309 A, hereinafter “Li”) Hinz et al. (US 20250117968 A1, hereinafter “Hinz”) (US 20240046422 A1, hereinafter “Song”) (CN 116993610 A, hereinafter “Su”) Claim Rejections - 35 USC § 112 07-30-02 AIA 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. 07-34-01 Claims 3-4, 10-11, 17-18 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 3 recites in part “ substantially pure noise” which is a relative term since applicant has not established what the range the term covers and the office has no way of ascertaining it since anyone has his or her own as to what is considered substantially pure noise or Gaussian noise. Appropriate explanation and/re correction are respectfully requested. Claims 10 and 17 contains similar limitation and are rejected on the same ground as claim 1 above. Claim 2, 11 and 18 depend at lest on either claim 1, 10 and 17 and are therefore not allowable for the same reason. Claim Rejections - 35 USC § 103 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 1-2, 5-9, 12-16, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (CN 114549309 A, hereinafter “Li”) in view of Hinz et al. (US 20250117968 A1, hereinafter “Hinz”)and in view of Song et al. (US 20240046422 A1, hereinafter “Song”) . Regarding claims 1, 8 and 15: Li teaches a method comprising: obtaining, using at least one processing device of an electronic device, an input image ( Li [0010]-[0016], claim 1, where Li teaches inputing the data into the low-resolution image LR and the high-resolution reference image Ref, wherein the output target is the super-resolution image SR); up-scaling, using the at least one processing device, the input image to generate an up- sampled image ( ( Li [0010]-[0016], claim 1, where Li teaches using double three times interpolation method to sample LR on low quality image LR of size of reference image); degrading, using the at least one processing device, the up-sampled image to generate a degraded up-sampled image (Li [0010]-[0016], claim 1, where Li teaches using the same interpolation operator to perform 8 times down sampling degradation and up-sampling interpolation operation to Ref, obtaining low quality reference image Ref); combining, using the at least one processing device, the up-sampled image and the degraded up-sampled image to generate combined data (Li [0010]-[0016], [0099]-[0100], claim 1, where Li teaches using super-resolution model to process LR under the assistance of LR1 RefrRef, Ref, obtaining SR result); and Li fails to explicitly teach generating, using the at least one processing device, an output image based on the combined data, the output image generated using a diffusion model. However, Hinz teaches a high-resolution image generation using diffusion models wherein obtaining a prompt; generating, using a first diffusion model, a predicted denoised image at a first resolution based on the prompt, wherein the predicted denoised image is generated at a first intermediate diffusion step of the first diffusion model; upsampling the predicted denoised image to obtain an upsampled denoised image at a second resolution that is higher than the first resolution; and generating, using a second diffusion model, an output image at the second resolution based on the prompt and the upsampled denoised image (Hinz [0003], claim 1, figs. 2, 8 and 9). Song further teaches a pseudo inverse for data restauration wherein the diffusion model 260 processes the input data to predict denoised input data {circumflex over (x)}.sub.t. In an embodiment, the diffusion model 260 is pre-trained. The pseudoinverse guidance computation unit 265 receives the denoised input data and degraded data (measurement y) that is a degraded version of reference data x.sub.0. The reference data is the desired output data, such as the reconstructed images 125, 130, and 135. The degraded image 120 is an example of degraded data. A function is applied to produce the noisy or degraded data y. In an embodiment, the degraded data is obtained as a function h of x.sub.0, i.e., y=h(x.sub.0). The function h is a data corruption process and can take different forms depending on the application, such as reduced resolution when the task is to perform super-resolution, and masking when the task is to perform inpainting (Song [0026]-[0031], figs 2-3). Therefore, taking the teachings of Li, Hinz and song as a whole, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to generate the super resolution image using diffusion model, since A diffusion model is a machine learning model that is well-suited for image generation. In some cases, a diffusion model works by gradually removing a Gaussian distribution of noise from a noisy image in a series of diffusion steps according to the diffusion model's predictions of what a denoised image should look like. As the series of diffusion steps progresses, the diffusion model's prediction of the denoised image becomes increasingly accurate (Hinz [0002]). Regarding claims 2, 9 and 16: Li in view of Hinz and in view of Song teaches wherein degrading the up-sampled image comprises: applying a forward diffusion process to the up-sampled image (Hinz [0009], Song [0119]). Regarding claims 5, 12 and 19 Li in view of Hinz and in view of Song teaches wherein combining the up-sampled image and the degraded up-sampled image comprises performing at least one of a concatenation or an addition of the up-sampled image and the degraded up-sampled image (Li [0010]-[0016], [0098]-[0100], claim 1, where Li teaches using super-resolution model to process LR under the assistance of LR1 RefrRef, Ref, obtaining SR result; In order to obtain better feature information extracting effect, TFSR uses cross-scale feature fusion (cross scalelike feature merge, CSFM) module to realize the cross-scale of the feature information CSFM receiving feature map input of different scales (16, 32, 64, 128), after cross-scale of the feature information-scale fusion processing, obtaining the feature map data of the corresponding scale by convolution mapping. The feature map of each size in the CSFM is received from feature information dimensions by the up-sampling/down-sampling operation, and the output feature map of the corresponding size is processed by the convolution layer after the matrix is connected in parallel.) Regarding claims 6, 13 and 20: Li in view of Hinz and in view of Song teaches wherein degrading the up-sampled image comprises adding Gaussian noise to the up-sampled image (Song [0018], [0034]-[0036]). Regarding claims 7 and 14: Li in view of Hinz and in view of Song teaches wherein the output image represents a super-resolution version of the input image (Li claim 1; Hinz [0112]) . 07-21-aia AIA Claim s 3-4, 10-11, 17-18 are rejected under 35 U.S.C. 103 as being unpatentable over Li et al. (CN 114549309 A, hereinafter “Li”) in view of Hinz et al. (US 20250117968 A1, hereinafter “Hinz”)and in view of Song et al. (US 20240046422 A1, hereinafter “Song”) and in view of Su et al. (CN 116993610 A, hereinafter “Su”) . Regarding claims 3, 10 and 17: Li in view of Hinz and in view of Song fails to explicitly teaches wherein: the forward diffusion process is capable of converting an image into substantially pure noise if at least a specified number of iterations are performed; and applying the forward diffusion process to the up-sampled image comprises performing less than the specified number of iterations using the up-sampled image in order to degrade the up-sampled image without converting the up-sampled image into pure noise (Hinz [0009], Song [0119]). However, Song teaches the data restoration system 200 comprises a diffusion model 260, a pseudoinverse guidance computation unit 265, and an output image unit 270. In an embodiment, the input data x.sub.T is initial noise (such as Gaussian noise). The diffusion model 260 processes the input data to predict denoised input data {circumflex over (x)}.sub.t (Song [0018], [0024], [0026], [0030], [0034]-[0035], [0038], [0041], [0047]-[0048]). Su further teaches the forward diffusion structure input is an image pair, that is, a matched low-dose CT image/sparse-angle CT image and a clean CT image, the low-dose image/sparse-angle image is called LR, the normal-dose image is called HR, the forward diffusion process is gradually adding noise to the image, the Markov chain is completed, and the reverse reasoning de-noising process starts from the step T, gradually reasoning de-noising, the input is the pure noise image yt generated in the forward diffusion process and the low quality image LR, the LR image is used as the condition guiding model to generate, the model iteration gradually removes the noise to obtain yt-1, yt-2, the whole process converts the standard normal distribution into empirical distribution, finally restoring to obtain the reconstructed CT image; wherein t is the diffusion times of the forward process (Su claim 1). Therefore, taking the teachings of Li, Hinz, Song and Su as whole, it would have been obvious to one of ordinary skill in the art before the effective filing date of the application to convert the converting an image into pure noise if at least a specified number of iterations are performed and performed less than the specified number of iterations using the up-sampled image in order to degrade the up-sampled image without converting the up-sampled image into pure noise, in order to render the system more efficient and/or less power intensive. Regarding claims 4, 11 and 18: Li in view of Hinz, in view of Song and in view of Su teaches wherein performing less than the specified number of iterations comprises performing between 75% and 95% of the specified number of iterations (Song [0018], [0024], [0026], [0030], [0034]-[0035], [0038], [0041], [0047]-[0048]; Su claim 1). Conclusion Any inquiry concerning this communication or earlier communications from the examiner should be directed to WEDNEL CADEAU whose telephone number is (571)270-7843. The examiner can normally be reached Mon-Fri 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, Chieh Fan can be reached at 571-272-3042. 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. /WEDNEL CADEAU/Primary Examiner, Art Unit 2632 April 18, 2026 Application/Control Number: 18/737,450 Page 2 Art Unit: 2632 Application/Control Number: 18/737,450 Page 3 Art Unit: 2632 Application/Control Number: 18/737,450 Page 4 Art Unit: 2632 Application/Control Number: 18/737,450 Page 5 Art Unit: 2632 Application/Control Number: 18/737,450 Page 6 Art Unit: 2632 Application/Control Number: 18/737,450 Page 7 Art Unit: 2632 Application/Control Number: 18/737,450 Page 8 Art Unit: 2632 Application/Control Number: 18/737,450 Page 9 Art Unit: 2632
