DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 08/07/2026 has been entered.
Response to Arguments
Applicant's arguments filed 08/07/2026 regarding the 35 USC 103 rejections with respect to the amended limitations of claims 1-12, 14-21 have been considered but they are not persuasive.
Applicant argues RE the amended limitations of independent claim 1 “generating an avatar representing the user based on the first sequence of images of the portion of the user, the avatar representing the user being based on a model including a vertex, the vertex being associated with at least one of a color or a density based on the first sequence of images;… and based on the second sequence of images, modifying the avatar representing the user with a displacement of the vertex to represent a gesture of the avatar representing the user.” in pages 7-8 against the references individually. In response, the examiner contests that one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). Here combined teachings of Chen, Gafni and Grabli are relied upon to address the limitations as a whole. As cited in the prior office action Chen teaches A method (Fig 1, abstract) comprising: receiving a first sequence of images of a user, the first sequence of images being monocular images (Fig 1, abstract, page 2 col 2); generating an avatar representing the user based on the first sequence of images, the avatar representing the user being based on a model including a vertex, the vertex being associated with at least one of a color or a density based on the first sequence of images (Fig 1, abstract, page 2 col 2).
Chen is silent RE: images of a portion of a user. However Gafni teaches receiving a first sequence of images of a portion of a user and extracting nerf in order to generate a facial mesh from the portion images in Abstract Fig 1. Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen a system and method of receiving a sequence of images of the portion of the user, as suggested by Grabli, in order to generate the avatar corresponding to the portion of the avatar eg, a facial avatar model to synthesize novel head poses as well as changes in facial expressions and thereby increasing system effectiveness and user experience.
It would have been further obvious to one of ordinary skill in the art that once Grabli is applied to Chen to generate the facial mesh from the portrait images, it would generate the avatar representing the user based on the first sequence of the images of the portions of the user effectively utilizing the facial avatar, to effectively synthesize novel head poses as well as changes in facial expressions.
Chen as modified by Gafni is silent RE: receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar. However Grabli teaches receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar in abstract, [0011], [0031], [0041] to identify and transfer the facial expressions of the user to the avatar. This is readily available or can equally be applied, as both Chen (page 2 col 2) and Gafni (Fig 2) readily teaches pose/expression generation deformation of spatial points using the 3D model for generating different corresponding pose as the gestures to reconstruct dynamic human/expressions. Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen as modified by Gafni a system and method of receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar, as suggested by Grabli, in order to generate different avatar gestures and thereby increasing system effectiveness and user experience.
Applicant further argues in page 8 RE the amended limitations of independent claim 10 that “the art of record does not disclose, "based on a difference between a location of a portion of the user in the first sequence of images, from which a neutral expression was determined, and a location of the portion of the user in the second sequence of images, from which a gesture of the avatar is determined, modify the avatar with a displacement of the vertex to represent the gesture of the avatar," as recited in claim 10, as amended. As discussed above with respect to claim 1, the art of record does not disclose or suggest any relationship between "the user in the first sequence of images, from which a neutral expression was determined," and, "the user in the second sequence of images, from which a gesture of the avatar is determined," as recited in claim 10, as amended.” In response, the Examiner contests that Chen as modified by Gafni and Grabli clearly teaches based on a difference between a location of a portion of the user in the first sequence of images, from which a neutral expression was determined, see Chen Figs 1, 4-6, 9-10, page 2 col 2- page 3 col 2, Gafni Figs 1- 3, Grabli Fig 5, [0032], [0043] etc wherein the initial facial mesh is generated utilizing the portion of the user images in canonical space/pose to derive a neutral expression. Chen as modified by Gafni and Grabli further teaches based on a difference between a location of a portion of the user in the first sequence of images, a location of the portion of the user in the second sequence of images, from which a gesture of the avatar is determined, modify the avatar with a displacement of the vertex to represent the gesture of the avatar (Chen Figs 1, 4-6, page 2 col 2- page 3 col 2, Gafni Figs 1- 3 and Grabli Fig 5, [0009] , [0031]-[0032], [0044], [0066] etc wherein pose/expression generation deformation of spatial points using the 3D model for generating different corresponding pose as the gestures to reconstruct dynamic gesture/expressions, applying the location difference (vertices movement, offset) according to pose-guided deformation with motion/facial tracking representing the pose/ gesture in the second sequence of images).
Therefore as clearly set forth above, the applied references satisfies the claimed requirement rejection of the claims 1 and 10 are maintained. Dependent claims 2-9, 11-12, 14-16, 21 also stand rejected depending on rejected base claims 1 and 10.
Applicant also argues in page 8 RE the amended limitations of independent claim 17 that “the art of record does not disclose or suggest generating and storing an avatar "in association with a user," in conjunction with modifying the avatar "in association with the session with the user," as recited in claim 17, as amended. The Examiner contests that Chen as modified by Gafni and Grabli at least teaches store the avatar in association with the user (Chen Figs 1, 4-6, abstract, introduction, page 1 col 1, Gafni Fig 1, and Grabli Fig 5, [0009], [0031]-[0032], [0044] etc. wherein reconstruction of the new pose of the avatar indicates storing the avatar, typical in any animation, gaming/virtual environment. And receive a second sequence of images of the portion of the user; and based on the second sequence of images, modify the avatar with a displacement of the vertex to represent a gesture of the avatar (Chen Figs 1, 4-6, page 2 col 2- page 3 col 2, Gafni Figs 1- 3 and Grabli Fig 5, [0009] , [0031]-[0032], [0044], [0066] etc wherein pose/expression generation deformation of spatial points using the 3D model for generating different corresponding pose as the gestures to reconstruct dynamic gesture/expressions, applying the location difference (vertices movement, offset) according to pose-guided deformation with motion/facial tracking representing the pose/ gesture in the second sequence of images).
Applicant's remaining arguments regarding the 35 USC 103 rejections with respect to amended limitations of claims 17-20 “in association with a session with the user, receive a second sequence of images of the portion of the user; and based on the second sequence of images, modify the avatar with a displacement of the vertex to represent a gesture of the avatar in association with the session with the user.” have been considered but are moot in view of the new ground(s) of rejection to teach the amended limitations necessitated by the amendment.
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.
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.
Claims 1-6, 8-12, 14-15, 21 are rejected under 35 U.S.C. 103 as being unpatentable over Chen et al (Chen J, Zhang Y, Kang D, Zhe X, Bao L, Jia X, Lu H. Animatable neural radiance fields from monocular rgb videos. arXiv preprint arXiv:2106.13629. 2021 Jun 25.), in view of Gafni et al (Gafni, Guy, et al. "Dynamic neural radiance fields for monocular 4d facial avatar reconstruction." Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2021, Applicant cited) and further in view of Grabli et al (US 20200286284 A1).
RE claim 1, Chen teaches A method (Fig 1, abstract) comprising:
receiving a first sequence of images of a user, the first sequence of images being monocular images (Fig 1, abstract, page 2 col 2);
generating an avatar representing the user based on the first sequence of images, the avatar representing the user being based on a model including a vertex, the vertex being associated with at least one of a color or a density based on the first sequence of images (Fig 1, abstract, page 2 col 2);
Chen is silent RE: images of a portion of a user.
However Gafni teaches receiving a first sequence of images of a portion of a user and extracting nerf in order to generate a facial mesh from the portion images in Abstract Fig 1.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen a system and method of receiving a sequence of images of the portion of the user, as suggested by Grabli, in order to generate the avatar corresponding to the portion of the avatar eg, a facial avatar model to synthesize novel head poses as well as changes in facial expressions and thereby increasing system effectiveness and user experience.
It would have been further obvious to one of ordinary skill in the art that once Grabli is applied to Chen to generate the facial mesh from the portrait images, it would generate the avatar representing the user based on the first sequence of the images of the portions of the user effectively utilizing the facial avatar, to effectively synthesize novel head poses as well as changes in facial expressions.
Chen as modified by Gafni is silent RE: receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar representing the user with a displacement of the vertex to represent a gesture of the avatar representing the user.
However Grabli teaches receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar in abstract, [0011], [0031], [0041] to identify and transfer the facial expressions of the user to the avatar. This is readily available or can equally be applied, as both Chen (page 2 col 2) and Gafni (Fig 2) readily teaches pose/expression generation deformation of spatial points using the 3D model for generating different corresponding pose as the gestures to reconstruct dynamic human/expressions.
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen as modified by Gafni a system and method of receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar representing the user with a displacement of the vertex to represent a gesture of the avatar representing the user, as suggested by Grabli, in order to generate different avatar gestures and thereby increasing system effectiveness and user experience.
RE claim 2, Chen as modified by Gafni and Grabli teaches, wherein the modifying the avatar with the displacement of the vertex includes: determining a vertex location of the model of an expression avatar based on the second sequence of images; determining displacement of the vertex based on the vertex location of the model of the expression avatar and a location of the vertex; and modifying the location of the vertex based on the displacement of the vertex (Grabli [0031]-[0032]).
RE claim 3, Chen as modified by Gafni and Grabli teaches, further comprising determining a color of a three-dimensional point of the avatar based on colors of multiple nearest-neighbor vertices of the three-dimensional point, the multiple nearest-neighbor vertices of the three-dimensional point including the vertex (Chen Fig 1, page 2 col 2, page 3 col 2).
RE claim 4, Chen as modified by Gafni and Grabli teaches, further comprising determining the displacement of the vertex based on a difference between a feature of the portion of the user in the first sequence of images and a feature of the portion of the user in the second sequence of images (Grabli Fig 5, [0044], [0084], [0086]).
RE claim 5, Chen as modified by Gafni and Grabli teaches, wherein: the model includes a three-dimensional morphable model configured to be translated into a two-dimensional representation for presentation on a computer display; and the vertex is a mesh vertex included in the three-dimensional morphable model (Chen Fig 1, page 3 col 1-2, Grabli [0003], [0006]).
RE claim 6, Chen as modified by Gafni and Grabli teaches, further comprising: determining an expression vertex location within an expression avatar based on the second sequence of images; and determining the displacement of the vertex based on the expression vertex location and a location of the vertex (Grabli Fig 5, [0031]-[0032], [0044]).
RE claim 8, Chen as modified by Gafni and Grabli teaches, wherein the model includes a triangle mesh and the vertex is included in a triangle in the triangle mesh (Chen Fig 1, page 3 col 1-2 and Grabli [0066]).
RE claim 9, Chen as modified by Gafni and Grabli teaches, wherein the gesture of the avatar includes a facial expression (Grabli Fig 5, [0031]-[0032], [0044]).
RE claim 21, Chen as modified by Gafni and Grabli teaches, wherein the vertex is associated with both the color and the density based on the first sequence of images (Chen Fig 1, page 2 col 2, page 3 col 2).
Claims 10-12, 14-15 recite limitations similar in scope with limitations of claims 4, 2-3, 5-6 and therefore rejected under the same rationale. In addition Chen as modified by Gafni and Grabli teaches A non-transitory computer-readable storage medium comprising instructions stored thereon (Chen abstract, Fig 1, wherein method steps are typically stored in CRM, eg., Grabli Fig 7, [0135]). Chen as modified by Gafni and Grabli further teaches based on a difference between a location of a portion of the user in the first sequence of images, from which a neutral expression was determined (Chen Figs 1, 4-6, 9-10, page 2 col 2- page 3 col 2, Gafni Figs 1- 3, Grabli Fig 5, [0032], [0043] etc wherein the initial facial mesh is generated utilizing the portion of the user images in canonical space/pose to derive a neutral expression); and a location of the portion of the user in the second sequence of images, from which a gesture of the avatar is determined, modify the avatar with a displacement of the vertex to represent the gesture of the avatar (Chen Figs 1, 4-6, page 2 col 2- page 3 col 2, Gafni Figs 1- 3 and Grabli Fig 5, [0009] , [0031]-[0032], [0044], [0066] etc wherein pose/expression generation deformation of spatial points using the 3D model for generating different corresponding pose as the gestures to reconstruct dynamic gesture/expressions, applying the location difference (vertices movement, offset) according to pose-guided deformation with motion/facial tracking representing the pose/ gesture in the second sequence of images).
Claims 7, 16 are rejected under 35 U.S.C. 103 as being unpatentable over Chen as modified by Gafni and Grabli, and further in view of Planche et al (US 20240029867 A1).
RE claim 7, Chen as modified by Gafni and Grabli teaches, wherein generating the avatar includes applying a neural network to the first sequence of images to determine the color or density associated with the vertex (Chen Fig 1, abstract).
Chen as modified by Gafni and Grabli is silent RE using a convolutional neural network. However Planche teaches in [0019] to predict the image properties of the multiple 3D points (vertices).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen as modified by Gafni and Grabli a system and method of applying a convolutional neural network, as suggested by Planche, in order to effectively predict/compute the nerf and color/density applying a typical CNN and thereby increasing system effectiveness and user experience.
Claim 16 recites limitations similar in scope with limitations of claim 7 and therefore rejected under the same rationale.
Claims 17-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chen as modified by Gafni, Grabli, and Planche, as applied in rejection of claim 7, and further in view of Chen Wenyu et al (US 20230222721 A1).
Claims 17-20 recite limitations similar in scope with limitations of claims 7, 2-4 and therefore rejected under the same rationale. In addition Chen as modified by Gafni and Grabli teaches A computing system comprising: at least one processor; and a non-transitory computer-readable storage medium comprising instructions stored thereon (Chen abstract, Fig 1, wherein method steps are implemented with a typical computing system, eg. Grabli Fig 7, [0132]), and store the avatar in association with the user (Chen Figs 1, 4-6, abstract, introduction, page 1 colo1, Gafni Fig 1, and Grabli Fig 5, [0009], [0031]-[0032], [0044] etc. wherein reconstruction of the new pose of the avatar indicates storing the avatar, typical in any animation, gaming/virtual environment.
Chen as modified by Gafni and Grabli is silent RE in association with a session with the user. However Chen Wenyu teaches generate a modified video stream depicting a digital representation of the first video conference participant in an avatar form in abstract, [0068]-[0070].
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to include in Chen as modified by Gafni and Grabli a system and method of where in the second sequence of images is in association with a session with the user, as suggested by Chen Wenyu, in order to extend the applicability of system to the video conference applications and thereby increasing system effectiveness and user experience.
It would have been further obvious to one of ordinary skill in the art that once Chen Wenyu is applied to the video conference system as set forth above, it would generate the corresponding gesture/change in facial expressions of the second sequence of the images in association with a session with the user for effectively depict each of the motion/gesture of the user.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure (see attached 892).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SULTANA MARCIA ZALALEE whose telephone number is (571)270-1411. The examiner can normally be reached Monday- Friday 8:00am-4:30pm.
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, Kent Chang can be reached at (571)272-7667. 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.
/Sultana M Zalalee/ Primary Examiner, Art Unit 2614
Prosecution Insights