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 .
Application Status
This office action is responsive to the Application No.:19019300 filed on 01/13/2025.
Claims 1-20 are pending and presented for examination.
This action has been made NON-FINAL.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 01/29/2025 is being considered by the examiner. A signed IDS is hereby attached.
Allowable Subject Matter
Claims 6, 7, 16 and 17 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter: The closest prior art references failed to disclose the following claim limitations:
wherein: the machine learning model comprises a transformer neural network, and the input comprises a first set of tokens corresponding to a first set of vertices in the deformed template shape and a second set of tokens corresponding to a second set of vertices in the neutral target shape COMBINED WITH wherein: the machine learning model comprises a spatial diffusion layer, a set of spatial gradient features, and a multilayer perceptron, and the input comprises a first set of geometric properties associated with the deformed template shape and a second set of geometric properties associated with the neutral target shape.
Claim Rejections - 35 USC § 103
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.
Claim(s) 1-5, 8-15 and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chu, US Patent Application No.: US 20240378836 in view of Hodges, US Patent Application No.: US 20230079478.
Claim 1:
Chu a computer-implemented method for generating a shape (See Chu Abstract; Paragraphs 0012-0017; 0021-0026; 0030). Chu failed to explicitly disclose “a non-neutral expression” and “machine learning”. However, Hodges discloses this feature in Paragraphs 0053 and 0067. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Chu by the teachings of Hodges to enable improved computer animation for managing facial deformations, more effectively. In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as computer animations (i.e. facial deformation). This close relation between both references highly suggests an expectation of success.
As modified:
The combination of Chu and Hodges discloses the following:
determining (i) a deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 00301) corresponding to a non-neutral expression on a template subject (See Hodges Paragraph 0053) and (ii) a neutral target shape corresponding to a neutral expression on a target subject (See Chu Paragraphs 00252; 0030);
generating input representing the deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 00303) and the neutral target shape (See Chu Paragraphs 00254; 0030);
and generating, via execution of a machine learning model based on the input (See Hodges Paragraph 0067), a deformed target shape corresponding to the non-neutral expression (See Hodges Paragraph 0053) on the target subject (See Chu Paragraphs 00255; 0030).
Claim 2:
The combination of Chu and Hodges discloses training the machine learning model (See Hodges Paragraph 0067) based on one or more losses computed between the deformed target shape (See Chu Paragraphs 00256; 0030; 0199) and a ground truth shape (See Chu Paragraphs 0014; 0138; 0216; 0218) corresponding to the non-neutral expression (See Hodges Paragraph 0053) on the target subject (See Chu Paragraphs 00257; 0030).
Claim 3:
The combination of Chu and Hodges discloses computing a set of displacements (See Chu Paragraphs 0167-0172) between the neutral target shape (See Chu Paragraphs 00258; 0030) and the ground truth shape (See Chu Paragraphs 0014; 0138; 0216; 0218); and generating the deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030) based on the set of displacements (See Chu Paragraphs 0167-0172) and a set of blendshapes (See Chu Paragraphs 0054; 0057; 0132) associated with the template subject (See Chu Paragraphs 00259; 0030).
Claim 4:
The combination of Chu and Hodges discloses wherein generating the deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030) comprises: transferring the set of displacements (See Chu Paragraphs 0167-0172) to a neutral template shape (See Chu Paragraphs 002510; 0030) corresponding to the neutral expression on the template subject (See Chu Paragraphs 002511; 0030) to generate an initial deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030); and generating the deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030) as a combination of the set of blendshapes (See Chu Paragraphs 0054; 0057; 0132) that matches the initial deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030).
Claim 5:
The combination of Chu and Hodges discloses wherein the one or more losses comprise a mean squared error (See Chu Paragraph 0183).
Claim 8:
The combination of Chu and Hodges discloses wherein: the input comprises a first set of points in the deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030) and a second set of points in the neutral target shape (See Chu Paragraphs 002512; 0030), and the machine learning model (See Hodges Paragraph 0067) generates a set of displacements associated with the second set of points (See Chu Paragraphs 0167-0172).
Claim 9:
The combination of Chu and Hodges discloses wherein the deformed template shape is determined via at least one of a scanning technique or a sculpting technique (See Chu Paragraphs 0048-0051).
Claim 10:
The combination of Chu and Hodges discloses wherein the template subject comprises a first face and the target subject comprises a second face (See Chu Figure 4; Paragraph 0059; 0142).
Claim 11:
Claim 11 is rejected on the same basis as claim 1.
Claim 12:
The combination of Chu and Hodges discloses wherein the instructions further cause the one or more processors to perform the steps of: generating a plurality of deformed template shapes associated with the template subject (See Chu Paragraphs 0012-0017; 0021-0026; 0030) based on (i) a plurality of neutral source shapes associated with a plurality of source subjects and (ii) a plurality of deformed source shapes associated with the plurality of source subjects (See Chu Paragraphs 0012-0017; 0021-0026; 0030); generating, via execution of a machine learning model (See Hodges Paragraph 0067), a plurality of training output shapes based on the plurality of deformed template shapes (See Chu Paragraphs 0012-0017; 0021-0026; 0030) and the plurality of neutral source shapes; and training the machine learning model (See Hodges Paragraph 0067) based on one or more losses computed between the plurality of training output shapes and the plurality of deformed source shapes (See Chu Paragraphs 0012-0017; 0021-0026; 0030) to generate the trained machine learning model (See Hodges Paragraph 0067).
Claim 13:
The combination of Chu and Hodges discloses wherein generating the plurality of deformed template shapes (See Chu Paragraphs 0012-0017; 0021-0026; 0030) comprises: computing a set of displacements (See Chu Paragraphs 0167-0172) between a neutral source shape included in the plurality of neutral source shapes (See Chu Paragraphs 002513; 0030) and a deformed source shape (See Chu Paragraphs 0012-0017; 0021-0026; 003014) included in the plurality of deformed source shapes (See Chu Paragraphs 0012-0017; 0021-0026; 003015); transferring the set of displacements (See Chu Paragraphs 0167-0172) to a neutral template shape (See Chu Paragraphs 002516; 0030) corresponding to the neutral expression on the template subject to generate an initial deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030); and generating a deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030) included in the plurality of deformed template shapes (See Chu Paragraphs 0012-0017; 0021-0026; 0030) as a combination of a set of blendshapes (See Chu Paragraphs 0054; 0057; 0132) for the template subject that matches the initial deformed template shape (See Chu Paragraphs 0012-0017; 0021-0026; 0030).
Claim 14:
The combination of Chu and Hodges discloses wherein the neutral source shape (See Chu Paragraphs 002517; 0030) corresponds to a neutral expression on a source subject included in the plurality of source subjects and the deformed source shape (See Chu Paragraphs 0012-0017; 0021-0026; 003018) corresponds to a second non-neutral expression on the source subject (See Hodges Paragraph 0053).
Claim 15:
The combination of Chu and Hodges discloses wherein the template subject and the plurality of source subjects comprise a plurality of faces (See Chu Figure 4; Paragraph 0059; 0142).
Claim 18:
The combination of Chu and Hodges discloses wherein the instructions further cause the one or more processors to perform the step of generating at least one of an animation (See Chu Paragraph 0024), an edited version of the deformed target shape, or a set of blendshapes (See Chu Paragraphs 0054; 0057; 0132) for the target subject based on the deformed target shape (See Chu Paragraphs 0012-0017; 0021-0026; 003019).
Claim 19:
The combination of Chu and Hodges discloses wherein the neutral target shape (See Chu Paragraphs 002520; 0030) is determined via at least one of a scanning technique or a sculpting technique (See Chu Paragraphs 0048-0051).
Claim 20:
Claim 20 is rejected on the same basis as claim 1.
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Hu, US Patent No.:10572720 relate to three-dimensional (3D) modeling, virtual human technology, and virtual reality. More specifically, various embodiments of the disclosure relate to a virtual reality-based apparatus and method to generate a 3D human face model using image and depth data.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEREE N BROWN whose telephone number is (571)272-4229. The examiner can normally be reached M-F 5:30-2:00 PM EST.
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, SAID BROOME can be reached at (571) 272-2931. 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.
/SHEREE N BROWN/Primary Examiner, Art Unit 2612 July 30, 2026
1 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
2 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
3 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
4 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
5 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
6 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
7 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
8 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
9 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
10 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
11 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
12 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
13 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
14 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
15 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
16 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
17 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
18 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
19 Paragraph 0016 of Chu recites “[0016] In some implementations, the using at least one surface-based deformation technique comprises performing wrap deformation to provide a wrap deformed version of the template avatar and selecting a sparse subset of deltas based on the wrap deformed version of the template avatar.”
20 Chu Paragraph 0025 recites “neutral poses of the target avatar.”
Prosecution Insights