DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA . In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Applicant’s submission filed on 02/04/2026 has been entered. Claims 1, 11, and 21 were amended. Claim 30 was canceled. Claim 31 was added. Claims 1-29 and 31 are pending in the application.
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, 6, 8, 10-11, 16, 18, 20-21, 26, 28, and 31 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu et al. (US 2025/0005836) in view of Wei et al. (US 2024/0312095) and Min et al. (US 2022/0137702).
Regarding claim 1, Chu teaches/suggests: A method of synthesizing facial features of a three-dimensional (3D) facial model (Chu [0064]-[0065] “Using the extracted features, the asset generation subsystem then generates a 3D model 220 of the avatar … For detailed facial animations, the asset generation subsystem creates a facial rig with blend shapes”), the method comprising:
obtaining a first frame, the first frame including a first portion of a face (Chu [0062] “Input data 201 is received in the form of audio, image, or video data”);
generating a first facial feature corresponding to the first portion of the face (Chu [0062]-[0063] “for images, the system uses computer vision techniques to analyze 2D pictures, detecting facial features ... Following data processing, the system moves on to feature extraction 210”);
obtaining a second frame, the second frame including a second portion of the face, wherein the second portion of the face at least partially overlaps the first portion of the face (Chu [0062] “When processing video input, the subsystem employs frame-by-frame analysis and motion tracking to capture dynamic aspects of appearance and movement”);
Chu is silent regarding:
generating a one-dimensional second facial feature corresponding to the second portion of the face,
wherein the first facial feature is higher-level dimensioned as compared to the one-dimensional second facial feature, and
generating a set of weights based on the one-dimensional second facial feature; and
applying the set of weights to the first facial feature to generate a weighted facial feature.
Wei, however, teaches/suggests:
generating a one-dimensional second facial feature corresponding to the second portion of the face (Wei [0027] “The trained machine learning model 208 may also output a predicted facial expression 212 based on the facial images 206” [0017] “A facial expression can be defined by a set of blendshape weights of a facial action coding system (FACS) … Blendshapes may also be referred to as facial action units and/or descriptors” [The facial expression meets the second facial feature.]),
generating a set of weights based on the one-dimensional second facial feature (Wei [0026] “A trained machine learning model 208 is applied to the facial images 206 to predict blendshape weights 210 for the wearer 102's facial expression 202”); and
applying the set of weights to the first facial feature to generate a weighted facial feature (Wei [0032] “The predicted blendshape weights 210 for the facial expression 202 of the wearer 102 of the HMD 100 can then be retargeted (228) onto a facial avatar corresponding to the face 104 of the wearer 102 to render the facial avatar with this facial expression 202”).
Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to modify the avatar of Chu to be retargeted as taught/suggested by Wei to render it with the facial expression. As such, Chu as modified by Wei teaches/suggests:
wherein the first facial feature is higher-level dimensioned as compared to the one-dimensional second facial feature (Chu [0062]-[0063] “for images, the system uses computer vision techniques to analyze 2D pictures, detecting facial features” Wei [0017] “A facial expression can be defined by a set of blendshape weights of a facial action coding system (FACS)”);
Chu is silent regarding:
wherein the second facial feature includes information about a specific portion of the face;
Min, however, teaches/suggests:
wherein the second facial feature includes information about a specific portion of the face (Min [0052] “Experiments on facial expressions are described below with reference to ‘Action Unit’ (AU) codes as specified by the Facial Action Coding System (FACS) ... FIG. 3 shows facial expressions corresponding to AU2 (outer brow raiser), AU4 (brow lowerer), AU6 (cheek raiser), AU12 (lip corner puller), AU15 (lip corner depressor) and AU18 (lip puckerer)”);
Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to modify the facial expression of Chu as modified by Wei to include information about the brow, cheek, and/or lip as taught/suggested by Min for realism.
Regarding claim 6, Chu as modified by Wei and Min teaches/suggests: The method of claim 1, wherein the one-dimensional second facial feature encodes an expression of the face (Wei [0027] “The trained machine learning model 208 may also output a predicted facial expression 212 based on the facial images 206”). The same rationale to combine as set forth in the rejection of claim 1 is incorporated herein.
Regarding claim 8, Chu as modified by Wei and Min teaches/suggests: The method of claim 1, further comprising generating a full facial texture based on the weighted facial feature (Chu [0066] “Using the input images and video, the system creates textures and materials 240 for the avatar's skin, hair, and clothing” Wei [0032] “The predicted blendshape weights 210 for the facial expression 202 of the wearer 102 of the HMD 100 can then be retargeted (228) onto a facial avatar corresponding to the face 104 of the wearer 102 to render the facial avatar with this facial expression 202”). The same rationale to combine as set forth in the rejection of claim 1 is incorporated herein.
Regarding claim 10, Chu as modified by Wei and Min teaches/suggests: The method of claim 1, wherein the first facial feature is generated by a first machine learning model (Chu [0063] “Convolutional Neural Networks (CNNs) are utilized to extract high-level features from visual data”) and the one-dimensional second facial feature is generated by a second machine learning model that is different from the first machine learning model (Wei [0027] “The trained machine learning model 208 may also output a predicted facial expression 212 based on the facial images 206”). The same rationale to combine as set forth in the rejection of claim 1 is incorporated herein.
Claims 11, 16, 18, and 20 recite limitation(s) similar in scope to those of claims 1, 6, 8, and 10, respectively, and are rejected for the same reason(s). Chu as modified by Wei and Min further teaches/suggests at least one memory; and at least one processor coupled to the at least one memory (Chu Fig. 10: CPU 21/GPU 22 and system memory 30).
Claims 21, 26, and 28 recite limitation(s) similar in scope to those of claims 1, 6, and 8, respectively, and are rejected for the same reason(s). Chu as modified by Wei and Min further teaches/suggests a non-transitory computer-readable medium having stored thereon instructions (Chu Fig. 10: system memory 30).
Regarding claim 31, Chu as modified by Wei and Min teaches/suggests: The method of claim 1, wherein the second portion of the face comprises a specific portion of the face (Chu [0062] “When processing video input, the subsystem employs frame-by-frame analysis and motion tracking to capture dynamic aspects of appearance and movement” Min [0052] “Experiments on facial expressions are described below with reference to ‘Action Unit’ (AU) codes as specified by the Facial Action Coding System (FACS) ... FIG. 3 shows facial expressions corresponding to AU2 (outer brow raiser), AU4 (brow lowerer), AU6 (cheek raiser), AU12 (lip corner puller), AU15 (lip corner depressor) and AU18 (lip puckerer)”). The same rationale to combine as set forth in the rejection of claim 1 is incorporated herein.
Claim(s) 2-3, 12-13, and 22-23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu et al. (US 2025/0005836) in view of Wei et al. (US 2024/0312095) and Min et al. (US 2022/0137702) as applied to claims 1, 11, and 21 above, and further in view of Li et al. (US 2021/0081755).
Regarding claim 2, Wei further discloses in [0040]: “there may be one convolutional neural network to predict the blendshape weights 506 from the extracted image features 526.” Chu, Wei, and Min are silent regarding: The method of claim 1, wherein the set of weights are generated by a set of fully connected layers of a machine learning model. Li, however, teaches/suggests the set of weights are generated by a set of fully connected layers of a machine learning model (Li [0227] “the learned weight of the features are more accurate by using techniques such as convolutional neural networks and multi-layer perceptrons”). Before the effective filing date of the claimed invention, the substitution of one known element (the MLP of Li) for another (the CNN of Wei) would have been obvious to one of ordinary skill in the art because such substitutions would have yielded predictable results, namely to learn the weights.
Regarding claim 3, Chu as modified by Wei, Min, and Li teaches/suggests: The method of claim 2, wherein the set of fully connected layers comprise a multilayer perceptron (Li [0227] “the learned weight of the features are more accurate by using techniques such as convolutional neural networks and multi-layer perceptrons”). The same rationale to combine as set forth in the rejection of claim 2 is incorporated herein.
Claims 12 and 13 recite limitation(s) similar in scope to those of claims 2 and 3, respectively, and are rejected for the same reason(s).
Claims 22 and 23 recite limitation(s) similar in scope to those of claims 2 and 3, respectively, and are rejected for the same reason(s).
Claim(s) 4-5, 14-15, and 24-25 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu et al. (US 2025/0005836) in view of Wei et al. (US 2024/0312095) and Min et al. (US 2022/0137702) as applied to claims 1, 11, and 21 above, and further in view of Zhang et al. (US 2024/0290025).
Regarding claim 4, Chu, Wei, and Min are silent regarding: The method of claim 1, wherein applying the set of weights comprise multiplying the set of weights with the first facial feature. Zhang, however, teaches/suggests multiplying the set of weights with the first facial feature (Zhang [0047] “The computing system can generate a weighted sum 510 by multiplying the radiance fields 506 by weights 508”). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to modify the retargeting of Chu as modified by Wei and Min such that the facial features are weighted as taught/suggested by Zhang to render the avatar with the facial expression.
Regarding claim 5, Chu as modified by Wei, Min, and Zhang teaches/suggests: The method of claim 4, wherein the first facial feature includes a set of channels including information about the first frame, and wherein weights of the set of weights are multiplied with channels of the set of channels (Zhang [0047] “The computing system can generate a weighted sum 510 by multiplying the radiance fields 506 by weights 508” [0051] “The feature vector can include values, such as a density value and one or more color values (such as a value for the color red, a value for the color green, and a value for the color blue)”). The RGB color values meet the set of channels. The same rationale to combine as set forth in the rejection of claim 4 is incorporated herein.
Claims 14 and 15 recite limitation(s) similar in scope to those of claims 4 and 5, respectively, and are rejected for the same reason(s).
Claims 24 and 25 recite limitation(s) similar in scope to those of claims 4 and 5, respectively, and are rejected for the same reason(s).
Claim(s) 7, 17, and 27 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu et al. (US 2025/0005836) in view of Wei et al. (US 2024/0312095) and Min et al. (US 2022/0137702) as applied to claims 1, 11, and 21 above, and further in view of Kang et al. (US 2024/0221254).
Regarding claim 7, Chu, Wei, and Min are silent regarding: The method of claim 1, wherein the one-dimensional second facial feature comprises a one-dimensional vector. Kang, however, teaches/suggests a one-dimensional vector (Kang [0036] “Features of one of multiple 1D vectors 112a, 112b, or 112n may comprise blend shape coefficients”). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to modify the facial expression of Chu as modified by Wei and Min to be the 1D vector as taught/suggested by Kang to organize it so that it can be used effectively.
Claims 17 and 27 recite limitation(s) similar in scope to those of claim 7, and are rejected for the same reason(s).
Claim(s) 9, 19, and 29 is/are rejected under 35 U.S.C. 103 as being unpatentable over Chu et al. (US 2025/0005836) in view of Wei et al. (US 2024/0312095) and Min et al. (US 2022/0137702) as applied to claims 1, 11, and 21 above, and further in view of Jiang et al. (US 2025/0111696).
Regarding claim 9, Wei further discloses in [0040]: “there may be one convolutional neural network to predict the blendshape weights 506 from the extracted image features 526.” Chu, Wei, and Min are silent regarding: The method of claim 1, wherein applying the set of weights to the first facial feature comprises applying the set of weights to an intermediate feature generated based on the first facial feature. Jiang, however, teaches/suggests applying the set of weights to an intermediate feature generated based on the first facial feature (Jiang [0062] “the spatial attention module is configured to perform attention calculation on the channel attention map in a feature map space (i.e., in a width-height dimension), that is, learn a weight for a local region on each space in the channel attention map, and multiply the weight to the channel attention map to obtain the spatial attention map. Finally, the spatial attention map may be input to the second convolution layer to obtain the global feature information”). Before the effective filing date of the claimed invention, it would have been obvious for one of ordinary skill in the art to modify the CNN of Chu as modified by Wei and Min to apply the weights as taught/suggested by Jiang for the learning.
Claims 19 and 29 recite limitation(s) similar in scope to those of claim 9, and are rejected for the same reason(s).
Response to Arguments
Applicant's arguments filed on 02/04/2026 have been fully considered but they are moot in view of the new ground(s) of rejection set forth in this Office action.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 2022/0108422 – facial model mapping
US 2023/0222721 – avatar generation
US 2026/0045031 – combine local and global features
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANH-TUAN V NGUYEN whose telephone number is 571-270-7513. The examiner can normally be reached on M-F 9AM-5PM ET. 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, JASON CHAN can be reached on 571-272-3022. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ANH-TUAN V NGUYEN/
Primary Examiner, Art Unit 2619
Prosecution Insights