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 .
Election/Restrictions
Applicant’s election without traverse of claims 1-7 and 13-19 in the reply filed on 03/16/2026 is acknowledged.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 03/28/2024 and 04/17/2024 are in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Objections
Claim 1 is objected to because of the following informalities: Line 8 recites “each noise sample” which Examiner suggests amending to “each of the training samples of noise” (since Line 4 recites “training samples of noise” – plural – versus Line 3 which recites “a noise sample” – singular). Appropriate correction is required.
Claim 2 is objected to because of the following informalities: Line 2 recites “to obtaining a transformed noise sample” which Examiner suggests amending to “to obtain a transformed noise sample”. Appropriate correction is required.
Claim 4 is objected to because of the following informalities: Line 1 recites “the editing step” which Examiner suggests amending to “the at least one editing step”. Lines 2 and 4 recite “the region of interest” which Examiner suggests amending to “the particular region of interest”. Appropriate correction is required.
Claim 13 is objected to because of the following informalities: Line 10 recites “each noise sample” which Examiner suggests amending to “each of the training samples of noise” (since Line 6 recites “training samples of noise” – plural – versus Line 3 which recites “a noise sample” – singular). . Appropriate correction is required.
Claim 14 is objected to because of the following informalities: Line 4 recites “when executed by one or more computers” which Examiner suggests amending to “when executed by the one or more computers”. Line 10 recites “each noise sample” which Examiner suggests amending to “each of the training samples of noise” (since Line 6 recites “training samples of noise” – plural – versus Line 3 which recites “a noise sample” – singular). . Appropriate correction is required.
Claim 15 is objected to because of the following informalities: Lines 6 and 7 recite “the image” which Examiner suggests amending to “the image to be edited” in order to provide consistency in the claim language. Appropriate correction is required.
Claim 16 is objected to because of the following informalities: Line 3 recites “the image” which Examiner suggests amending to “the image to be edited” in order to provide consistency in the claim language. Appropriate correction is required.
Claim 18 is objected to because of the following informalities: Line 3 recites “the images of the sequence” which Examiner suggests amending to “images of the sequence of images” (deleting “the” before “images”) in order to provide consistency and clarity in the claim language. Lines 4 and 5 recite “the image” which Examiner suggests amending to “the image to be edited” in order to provide consistency in the claim language. 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 1-7 and 13-19 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 recites the limitation "applying each…to one or more training images, to obtain a noisy image" in Line 8 and “the noise sample” in Lines 9 and 12. It is unclear as to which noise sample in Lines 9 and 12 is being referred to as there is a recitation of a noise sample (singular) in Line 3, but the noisy image is obtained by applying each of the training samples of noise (see claim 1 claim objection above) to one or more training images. It is also unclear as to whether a plurality of noisy images are obtained from the applying (consistent with Applicant’s Specification) or that a single noisy image is obtained from the applying. Examiner suggests amending the limitation to reflect an interpretation as is consistent with Applicant’s Specification. For purposes of examination, Examiner has interpreted the limitation in Line 8 to be applying each of the training samples of noise to one or more training images, to obtain one or more noisy images. Examiner notes that Lines 9 and 10 also recite “the noisy image” and whatever amendment is made to the limitation in Line 8 should be reflected in any amendments to “the noisy image” in Lines 9 and 10 and any amendments to “the noise sample” in Lines 9 and 12.
Claim 1 also recites the limitations "the to-be-trained diffusion model" in Lines 10 and 11 and “the behavior of the diffusion model” in Line 16. There is insufficient antecedent basis for these limitations in the claim as there is no earlier mention of a to-be-trained diffusion model (just training a diffusion model) or a behavior of the diffusion model. Examiner suggests amending the limitations to “the diffusion model” (deleting “to-be-trained”) and “a behavior of the diffusion model”, respectively, and has interpreted the limitations as such.
Claim 2 recites the limitation “the noise sample” in Line 2 and should be amended to reflect whatever amendment is made to the limitation in Line 8 of Claim 1 (see Claim 1 rejection above on “the noise sample”).
Claim 5 recites the limitation “the noise sample” in Line 2 and should be amended to reflect whatever amendment is made to the limitation in Line 8 of Claim 1 (see Claim 1 rejection above on “the noise sample”).
Claim 6 recites the limitation “the noise sample” in Line 3 and should be amended to reflect whatever amendment is made to the limitation in Line 8 of Claim 1 (see Claim 1 rejection above on “the noise sample”).
Claim 6 also recites the limitation "the weighting" in Line 2. There is insufficient antecedent basis for this limitation in the claim as there is no earlier mention of a weighting. Examiner suggests amending to “a weighting” and has interpreted the limitation as such.
Claims 3, 4, and 7 depend on claim 1 and thus are also rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite.
Claim 13 recites the limitation "applying each…to one or more training images, to obtain a noisy image" in Line 10 and “the noise sample” in Lines 11 and 14. It is unclear as to which noise sample in Lines 11 and 14 is being referred to as there is a recitation of a noise sample (singular) in Line 3, but the noisy image is obtained by applying each of the training samples of noise (see claim 13 claim objection above) to one or more training images. It is also unclear as to whether a plurality of noisy images are obtained from the applying (consistent with Applicant’s Specification) or that a single noisy image is obtained from the applying. Examiner suggests amending the limitation to reflect an interpretation as is consistent with Applicant’s Specification. For purposes of examination, Examiner has interpreted the limitation in Line 10 to be applying each of the training samples of noise to one or more training images, to obtain one or more noisy images. Examiner notes that Lines 11 and 12 also recite “the noisy image” and whatever amendment is made to the limitation in Line 10 should be reflected in any amendments to “the noisy image” in Lines 11 and 12 and any amendments to “the noise sample” in Lines 11 and 14.
Claim 13 also recites the limitations "the to-be-trained diffusion model" in Lines 12 and 13 and “the behavior of the diffusion model” in Line 17. There is insufficient antecedent basis for these limitations in the claim as there is no earlier mention of a to-be-trained diffusion model (just training a diffusion model) or a behavior of the diffusion model. Examiner suggests amending the limitations to “the diffusion model” (deleting “to-be-trained”) and “a behavior of the diffusion model”, respectively, and has interpreted the limitations as such.
Claim 14 recites the limitation "applying each…to one or more training images, to obtain a noisy image" in Line 10 and “the noise sample” in Lines 11 and 14. It is unclear as to which noise sample in Lines 11 and 14 is being referred to as there is a recitation of a noise sample (singular) in Line 3, but the noisy image is obtained by applying each of the training samples of noise (see claim 14 claim objection above) to one or more training images. It is also unclear as to whether a plurality of noisy images are obtained from the applying (consistent with Applicant’s Specification) or that a single noisy image is obtained from the applying. Examiner suggests amending the limitation to reflect an interpretation as is consistent with Applicant’s Specification. For purposes of examination, Examiner has interpreted the limitation in Line 10 to be applying each of the training samples of noise to one or more training images, to obtain one or more noisy images. Examiner notes that Lines 11 and 12 also recite “the noisy image” and whatever amendment is made to the limitation in Line 10 should be reflected in any amendments to “the noisy image” in Lines 11 and 12 and any amendments to “the noise sample” in Lines 11 and 14.
Claim 14 also recites the limitations "the to-be-trained diffusion model" in Lines 12 and 13 and “the behavior of the diffusion model” in Line 17. There is insufficient antecedent basis for these limitations in the claim as there is no earlier mention of a to-be-trained diffusion model (just training a diffusion model) or a behavior of the diffusion model. Examiner suggests amending the limitations to “the diffusion model” (deleting “to-be-trained”) and “a behavior of the diffusion model”, respectively, and has interpreted the limitations as such.
Claim 15 recites the limitations "the noise sample" in Lines 4 and 6 and “the input” in Line 9. There is insufficient antecedent basis for these limitations in the claim as it is unclear as to which noise sample is being referred to (as claim 1 discloses a noise sample and Line 4 of Claim 15 also recites a noise sample) and it is unclear as to which input is being referred to (as Claim 1 recites an input and Lines 7-8 of Claim 15 recites an input for the trained diffusion model). Examiner suggests amending the limitations to “the randomly drawn noise sample” and “the input for the trained diffusion model”, respectively, and has interpreted the limitations as such.
Claim 16 recites the limitation "the noise sample" in Line 1. There is insufficient antecedent basis for this limitation in the claim as it is unclear as to which noise sample is being referred to (as claim 1 discloses a noise sample and Line 4 of Claim 15 also recites a noise sample). Examiner suggests amending to “the randomly drawn noise sample” and has interpreted the limitation as such.
Claims 17-19 depend on claim 15 and thus are also rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite.
Allowable Subject Matter
Claims 1, 13, and 14 would be allowable if rewritten or amended to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action.
With regards to claims 1, 13, and 14, Hoogeboom et al. (Equivariant Diffusion for Molecule Generation in 3D) and Anand et al. (US 2023/0377690) disclose similar concepts of an equivariant diffusion model that is equivariant to a transform applied to data, however, these are in the field of generating molecules or protein sequence and structure generation and not in images and it would not be obvious for one of ordinary skill in the art to apply the same concept of a diffusion model for molecule generation or a diffusion model for protein sequence and structure generation to a diffusion model for generating a de-noised image. Park et al. (US 2024/0185037) discloses providing training samples of noise, providing training images, applying each noise sample to one or more training images to obtain a noisy image, generating, by the to-be-trained diffusion model, from the input, an output, computing an expected output, rating, using a predetermined loss function, a deviation of the output from the expected output, and optimizing parameters that characterize the behavior of the diffusion model towards a goal that when further training samples of noise are processed, a value of the loss function improves. However, there is no mention of providing at least one transform with respect to which the diffusion model shall be equivariant, applying the transform to the noisy image and/or to the noise sample before forming the noisy image to obtain an input for the to-be-trained diffusion model, and generating an output by the to-be-trained diffusion model from the obtained input. Johnson et al. (US 10,152,768) discloses training image transformation models and applying image transformation models to noisy frames to reduce artifacts, however, that is not the same as what is disclosed in the claim and there is no mention of obtaining a diffusion model. Liu et al. (CN 116543246) discloses providing training samples of noise and training images, providing a transform, applying each noise sample to a training image to obtain a noisy image, applying the transform to the noisy image, generating by the diffusion model, an output, computing an expected output, rating, using a loss function a deviation of the output from the expected output, and optimizing the parameters. However, it is unclear as to whether the diffusion model is equivariant with respect to the transform. In addition, this reference is not considered prior art as it was published after the effective filing date of the claimed invention. Thus, while different prior arts disclose parts of the claim, none of the prior arts disclose or have reasonable motivation to combine to disclose all of the limitations of the claim as a whole.
Claims 2-7 and 15-19 would be allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), 2nd paragraph, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
With regards to claims 2-7 and 15-19, they are dependent on claim 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Applicants are directed to consider additional pertinent prior art included on the Notice of References Cited (PTOL 892) attached herewith.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CAROL W CHAN whose telephone number is (571)272-5766. The examiner can normally be reached 9:30-3:30 M-F.
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, Sumati Lefkowitz can be reached at (571) 272-3638. 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.
/CAROL W CHAN/Primary Examiner, Art Unit 2672
Prosecution Insights