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 .
Response to Arguments
Applicant's arguments filed 04/02/2026 have been fully considered but they are not persuasive, with regards to all the claims being in condition for allowance. The Examiner points out that Applicant’s amendments (amendment to claim 1 and newly added claim 11) have overcome the previous 35 USC 101 rejections for claims 1-9 and 11. The filing and Approval of a Terminal Disclaimer filed on 04/02/2026 has overcome the previous Double Patent rejections for claims 1-11. However, the newly added amendments (to claim 1 and newly added claim 11) have introduced New Matter. Also, claim 10 has not been amended or canceled and thus is still rejected under 35 USC 101 as in the previous Office Action. Thus, the claims are not in condition for Allowance. The Examiner would also like to point out that during the interview on 02/26/2026 the Examiner stated that support for the new claim(s)/amendments would need to be pointed out within the Specification. Applicant’s arguments for Support for the amendments will now be addressed:
Applicant states (Remarks; p. 9, Section III., 1st paragraph) “Support for the amendments to Claim 1 is found, for example, in paragraphs [0004], [0008], and [0064] of the present application as published as US20240428615A1, which describe facial key-point extraction from input images, image reconstruction, annotation noise, and the resulting improvement in temporal continuity and image quality”. First, the Examiner would like to point out that paragraph [0004] is part of the “Background Art” and is describing other “conventional” inventions and not Applicant’s invention. Secondly, nowhere within the Specification or Drawings do the words “images”, “video” or “sequence” appear in the context of the claim language (“images” appears in [0058] but stating that the application is applied to a face image however it “may be applied to various other images”, showing still a single image and not that there are multiple/sequence of images used; “video” is only used in the “Background Art” in paragraph [0003], but does not talk about Applicant’s invention; and “sequence” does never appear). Paragraph [0008] just states “A neural network-based key point training apparatus according to an embodiment disclosed comprises a key point model trained to extract key points from an input image and an image reconstruction model trained to reconstruct the input image with the key points output by the key point model as the input”, which specifically states using just “an input image”. Paragraph [0064] states “Here, since the input image itself does not have noise over time (i.e., annotation noise) unlike the key points, it is possible to extract key points that are continuous and stable over time while training is in progress. In addition, as the accuracy of key point extraction is increased and key points stable over time are extracted, quality of the reconstructed image reconstructed by the image reconstruction model 104 may also be improved”, however, nowhere does it state that there are multiple images, and more specifically a “sequence of input images” since all the Specification talks about is a single “image”. Even the “over time while training” doesn’t support the claim language since at most it would show using the same single image over time and not a “sequence of input images”.
Applicant states (Remarks; p. 9, Section III., 2nd paragraph) “The recitation of processing a sequence of input images is supported by the disclosure of training on facial images in a lip-sync context and extracting key points that are continuous and stable over time (see, e.g., paragraphs [0003]-[0005], [0046])”. First, the Examiner would like to point out that paragraphs [0003-0005] are part of the “Background Art” and are describing other “conventional” inventions and not Applicant’s invention. Secondly, nowhere within the Specification or Drawings do the words “images”, “video” or “sequence” appear in the context of the claim language (“images” appears in [0058] but stating that the application is applied to a face image however it “may be applied to various other images”, showing still a single image and not that there are multiple/sequence of images used; “video” is only used in the “Background Art” in paragraph [0003], but does not talk about Applicant’s invention; and “sequence” does never appear). Lip-sync is another one which is only discussed within the “Background Art” in paragraph [0004]. Paragraph [0046] states “According to the embodiments disclosed, by performing training so that the key points are extracted from the input image in the key point model, and the input image is reconstructed from the key points of the key point model in the image reconstruction model, the key points that are continuous and stable over time can be extracted while training is in progress because the input image itself does not have noise over time (i.e., annotation noise) unlike the key points”. As discussed above, with regards to paragraph [0064], paragraph [0046] also does not state that there are multiple images, and more specifically a “sequence of input images” since all the Specification talks about is a single “image”. Even the “over time can be extracted while training” doesn’t support the claim language since at most it would show using the same single image over time and not a “sequence of input images”.
Applicant states (Remarks; p. 9, Section III., 3rd paragraph) “Support for new Claim 11 is found, for example, in paragraphs [0003], [0008], [0012], and [0046] of the published application, which describe lip-sync facial images corresponding to a voice message, training the key point model and image reconstruction model, and optimizing the combined objective function”. First, the Examiner would like to point out that paragraph [0003] is part of the “Background Art” and is describing other “conventional” inventions and not Applicant’s invention. Secondly, nowhere within the Specification or Drawings do the words “images”, “video” or “sequence” appear in the context of the claim language (“images” appears in [0058] but stating that the application is applied to a face image however it “may be applied to various other images”, showing still a single image and not that there are multiple/sequence of images used; “video” is only used in the “Background Art” in paragraph [0003], but does not talk about Applicant’s invention; and “sequence” does never appear). Lip-sync is another one which is only discussed within the “Background Art” in paragraph [0004]. “Utterance of a voice message” is another one which is only discussed within the “Background Art” in paragraph [0003]. Paragraph [0008] just states “A neural network-based key point training apparatus according to an embodiment disclosed comprises a key point model trained to extract key points from an input image and an image reconstruction model trained to reconstruct the input image with the key points output by the key point model as the input”, which specifically states using just “an input image”. Paragraph [0012] is the equation used within the claim language and does not show using a “sequence of images”, “lip sync” or that they correspond to an “utterance of a voice message". Paragraph [0046] states “According to the embodiments disclosed, by performing training so that the key points are extracted from the input image in the key point model, and the input image is reconstructed from the key points of the key point model in the image reconstruction model, the key points that are continuous and stable over time can be extracted while training is in progress because the input image itself does not have noise over time (i.e., annotation noise) unlike the key points”. Paragraph [0046] also does not state that there are multiple images, and more specifically a “sequence of input images” since all the Specification talks about is a single “image”. Even the “over time can be extracted while training” doesn’t support the claim language since at most it would show using the same single image over time and not a “sequence of input images”.
Claims 1-11 are pending; claim 1 has been amended; and claim 11 has been newly added.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claim 1 (and thus dependent claims 2-9) are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Independent claim 1 states to “(i) receive a sequence of input images including a face,(ii) for each input image in the sequence” … (i) receive, for each input image in the sequence, the key points output by the key point model” … “wherein, by training the key point model and the image reconstruction model using the sequence of input images, the apparatus is configured to extract key points that are continuous and stable over time and to reconstruct images with improved image quality”. As discussed above in the Response to Arguments, “sequence of input images” is not supported within the Specification. Appropriate correction is required.
Claim 11 is rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Independent claim 11 states “a sequence of facial images corresponding to an utterance of a voice message” … “(i) processing each facial image in the sequence” … “(i) inputting, for each facial image in the sequence” … “jointly optimizing the parameters of the key point model and the image reconstruction model by minimizing, over the sequence of facial images” … “wherein, by performing the training and joint optimization using the sequence of facial images, the method extracts facial key points that are continuous and stable over time despite annotation noise in labelled key points and improves image quality of reconstructed facial images used for generating a lip sync facial image corresponding to the voice message”. As discussed above in the Response to Arguments, “sequence of input images” (let alone “sequence of facial images”), “utterance of a voice message”, and “lip sync” are not supported within the Specification. Appropriate correction is required.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claim 10 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an
Abstract Idea without significantly more. The claim(s) recite(s) "models" which are merely computational processes for the input data (image); and wherein the calculation of the optimized parameters is purely a mathematical equation. This judicial exception is not integrated into a practical application because the data gathering steps required to use the optimization equation do not add a meaningful limitation to the method as they are insignificant extra-solution activity (also they are written passively; as the model is trained to "extract" and does not actually do any extracting). The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the "computing device", "one or more processors", and "memory" are well-understood, routine, conventional computer functions as recognized by the court decisions listed in MPEP § 2106.05(d).
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 mailing date of this final action.
Contact
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL J VANCHY JR whose telephone number is (571)270-1193. The examiner can normally be reached Monday - Friday 9am - 5pm.
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, Emily Terrell can be reached at (571) 270-3717. 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.
/MICHAEL J VANCHY JR/Primary Examiner, Art Unit 2666 Michael.Vanchy@uspto.gov
Prosecution Insights