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.
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, 9-13, and 17-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wedig et al. (US 2019/0362529) in view of Le et al. ("Smooth skinning decomposition with rigid bones." ACM Transactions on Graphics (TOG) 31.6 (2012): 1-10) and Bailey et al. (US 2021/0350621).
Regarding claim 1, Wedig teaches/suggests: A computer-implemented method to generate a linear blend skinning (LBS) rig for animation (Wedig [0155] “Linear blend skinning (LBS) is a common technique for animating digital puppets”), comprising:
for each pose p of a plurality of poses P and for each joint k of a plurality of joints J (Wedig [0156] “A relationship between the skeletal joints and a base (neutral) pose of that skeleton can be used to define an association between each vertex of the mesh and each of the joints in the skeleton”),
determining, by a processor (Wedig [0044] “The local processing and data module 260 may comprise a hardware processor”), a set of vertex-joint pairs in which a joint j of the plurality of joints J has influence over a vertex i in the pose p (Wedig [0156] “A weight map comprising a set of weights for every joint and every vertex can be used to measure the amount of influence of any joint on any vertex. If the joint does not influence a vertex, the associated weight is zero”);
determining, by the processor, a corresponding first LBS coefficient βi,j(p) for each vertex-joint pair in the set of vertex-joint pairs based on a rotational transform Rj(p) of the joint j, an initial vertex position vi(0) of the vertex i in a neutral pose, and a translational transform Tj(p) of the joint j (Wedig [0174] “The transformed coordinate v.sub.i.sup.′ for a point v.sub.i is the sum of the weighted transforms for each specific joint” [A weighted transform meets the first LBS coefficient.]);
determining, by the processor, a corresponding second LBS coefficient γi(p) for each vertex i in the set of vertex-joint pairs by summing first LBS coefficients βi,j(p) for each vertex-joint pair that correspond to that respective vertex i, where i=1,...,N, where N is a total number of vertices (Wedig [0174] “The transformed coordinate v.sub.i.sup.′ for a point v.sub.i is the sum of the weighted transforms for each specific joint”);
determining, by the processor, a rotational transform Rk(p) and a translational transform Tk(p) for the joint k (Wedig [0156] “the deformed mesh (representing the new pose) can be calculated by determining a relative transformation (e.g., a rotation and a translation) of each of the joints from their base pose to the new pose”);
rendering, by the processor, an avatar head based in the pose p based on the
Wedig does not teach/suggest:
determining, by the processor, a corresponding third LBS coefficient αi,k(p) for each vertex i and each joint k based on a final vertex position vi(p) of the vertex i in the pose p, and the corresponding second LBS coefficient γi(p) for vertex i, and a fourth LBS coefficient βi,k(p) corresponding to the vertex i and the joint k;
determining, by the processor, a rotational transform Rk(p) and a translational transform Tk(p) for the joint k based on the corresponding third LBS coefficient αi,k(p) for the joint k;
Le, however, teaches/suggests:
determining, by the processor, a corresponding third LBS coefficient αi,k(p) for each vertex i and each joint k based on a final vertex position vi(p) of the vertex i in the pose p, and the corresponding second LBS coefficient γi(p) for vertex i, and a fourth LBS coefficient βi,k(p) corresponding to the vertex i and the joint k (Le §3 ¶1 “The introduced Smooth Skinning Decomposition with Rigid Bones (SSDR) model of animated meshes aims to solve the inverse problem of the LBS model” §3.3 ¶5 “The problem of finding the optimal transformation then becomes: [Eq. 7]”);
determining, by the processor, a rotational transform Rk(p) and a translational transform Tk(p) for the joint k based on the corresponding third LBS coefficient αi,k(p) for the joint k (Le Eq. 7);
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 LBS model of Wedig to include the SSDR model of Le to solve the inverse problem.
Wedig further discloses in [0164]: “The process of learning the skinning parameters from the training data is sometimes referred to as joint decomposition.” Wedig as modified by Le does not teach/suggest:
updating, by the processor, the rotational Rk(p) and a translational transform Tk(p) for each joint k based on a learning rate λ; and
determining, by the processor, a final rotational transform and a final translational transform for joint k based on the rotational transform and the translational transform updated based on the learning rate λ;
Bailey, however, teaches/suggests a learning rate λ (Bailey [0103] “Optimization starts with the learning rate at 10.sup.−3”). 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 skinning of Wedig as modified by Le to include the learning rate of Bailey for the learning. As such, Wedig as modified by Le and Bailey teaches/suggests:
updating, by the processor, the rotational Rk(p) and a translational transform Tk(p) for each joint k based on a learning rate λ (Wedig [0175] “The goal of the joint decomposition process is to calculate the skinning parameters w.sub.ij, R.sub.j and T.sub.j in a way that reduces or minimizes an error between the transformed positions v.sub.i.sup.′ (calculated from Eq. (1)) and reference positions v.sub.i.sup.TD of these points in target poses in the training data” Le Eq. 7; Bailey [0103] “Optimization starts with the learning rate at 10.sup.−3”); and
determining, by the processor, a final rotational transform and a final translational transform for joint k based on the rotational transform and the translational transform updated based on the learning rate λ (Wedig [0175] “The goal of the joint decomposition process is to calculate the skinning parameters w.sub.ij, R.sub.j and T.sub.j in a way that reduces or minimizes an error between the transformed positions v.sub.i.sup.′ (calculated from Eq. (1)) and reference positions v.sub.i.sup.TD of these points in target poses in the training data” Le Eq. 7; Bailey [0103] “the parameters θ.sub.k from the coarse approximation are fully optimized” [In view of Wedig, Le, and Bailey, the optimized Eq. 6 meets the final rotational and translational transforms.]);
Regarding claim 2, Wedig as modified by Le and Bailey teaches/suggests: The method of claim 1, further comprising, for each pose p of a plurality of poses P and for each joint k of a plurality of joints J:
determining, by the processor, a set of final skinning weights for each vertex-joint pair in the set of vertex-joint pairs based on the final rotational transform and the final translational transform for each joint k of the plurality of joints J (Wedig [0175] “The goal of the joint decomposition process is to calculate the skinning parameters w.sub.ij, R.sub.j and T.sub.j in a way that reduces or minimizes an error between the transformed positions v.sub.i.sup.′ (calculated from Eq. (1)) and reference positions v.sub.i.sup.TD of these points in target poses in the training data” Le Eq. 7; Bailey [0103] “the parameters θ.sub.k from the coarse approximation are fully optimized”).
The same rationale to combine as set forth in the rejection of claim 1 is incorporated herein.
Regarding claim 3, Wedig as modified by Le and Bailey does not teach/suggest: The method of claim 1, wherein determining the set of vertex-joint pairs in which a joint j of the plurality of joints J has influence over the vertex i in the pose p comprises:
determining, by the processor, a i(0) of the vertex i in the neutral pose and the final vertex position vi(p) of the vertex i in the pose p for each of the plurality of poses P, the set of vertex-joint pairs being determined based on the learned from the training data”).
However, official notice is taken that the concept and advantages of a feature vector are well known and expected in the art. It would have been obvious for each vertex of Wedig as modified by Le and Bailey to include a feature vector for the learning.
Regarding claim 4, Wedig as modified by Le and Bailey does not teach/suggest: The method of claim 1, further comprising:
assigning, by the processor, an initial skinning weight wij to each vertex-joint pair in the set of vertex-joint pairs to a value of 1.
Le further teaches/suggests:
assigning, by the processor, an initial skinning weight wij to each vertex-joint pair in the set of vertex-joint pairs to a value of 1 (Le §3.1 ¶1 “we assumes no bone-vertex weight blending in the initialization step. With this assumption, each vertex is influenced by exactly one bone and its bone-vertex weight is exactly 1”).
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 weight map of Wedig as modified by Le and Bailey to be assigned as taught/suggested by Le for initialization.
Regarding claim 5, Wedig as modified by Le and Bailey teaches/suggests: The method of claim 4, wherein the corresponding first LBS coefficient βi,j(p) for each vertex-joint pair in the set of vertex-joint pairs is determined by solving [the claimed Eq.] (Wedig Eq. 1).
Claims 9-13 recite limitation(s) similar in scope to those of claims 1-5, respectively, and are rejected for the same reason(s). Wedig as modified by Le and Bailey further teaches/suggests a memory, coupled to the processor and storing instructions (Wedig [0044] “The local processing and data module 260 may comprise a hardware processor, as well as digital memory”).
Claims 17-19 recite limitation(s) similar in scope to those of claims 1 and 3-4, respectively, and are rejected for the same reason(s). Wedig as modified by Le and Bailey further teaches/suggests a non-transitory computer-readable medium storing instructions (Wedig [0044] “The local processing and data module 260 may comprise a hardware processor, as well as digital memory”).
Claim(s) 6-8, 14-16, and 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Wedig et al. (US 2019/0362529) in view of Le et al. ("Smooth skinning decomposition with rigid bones." ACM Transactions on Graphics (TOG) 31.6 (2012): 1-10) and Bailey et al. (US 2021/0350621) as applied to claims 5, 13, and 19 above, and further in view of Eisemann et al. (US 2017/0032055).
Regarding claim 6, Wedig as modified by Le and Bailey does not teach/suggest: The method of claim 5, wherein the corresponding second LBS coefficient γi(p) for each vertex i in the set of vertex-joint pairs is determined by solving [the claimed Eq.]. Eisemann, however, teaches/suggests j:wij>0 (Eisemann [0078] “Sparsity: only ‘few’ w.sub.ij>0; leads to simpler controls and a faster rendering process” [0099] “To sparsify the set of weights per vertex i, a bone index j should be removed from B(i) if weight w.sub.ij is small”). 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 insignificant bones of Wedig as modified by Le and Bailey to be removed as taught/suggested by Eisemann for faster rendering.
As such, Wedig as modified by Le, Bailey, and Eisemann teaches/suggests the corresponding second LBS coefficient γi(p) for each vertex i in the set of vertex-joint pairs is determined by solving [the claimed Eq.] (Wedig Eq. 1; Eisemann [0078] “Sparsity: only ‘few’ w.sub.ij>0; leads to simpler controls and a faster rendering process” [0099] “To sparsify the set of weights per vertex i, a bone index j should be removed from B(i) if weight w.sub.ij is small”).
Regarding claim 7, Wedig as modified by Le, Bailey, and Eisemann teaches/suggests: The method of claim 6, wherein the corresponding third LBS coefficient αi,k(p) for each vertex i and each joint k is determined by solving [the claimed Eq.] (Le Eq. 7; Eisemann [0078] “Sparsity: only ‘few’ w.sub.ij>0; leads to simpler controls and a faster rendering process” [0099] “To sparsify the set of weights per vertex i, a bone index j should be removed from B(i) if weight w.sub.ij is small”). The same rationales to combine as set forth in the rejection of claims 1 and 6 are incorporated herein.
Regarding claim 8, Wedig as modified by Le, Bailey, and Eisemann teaches/suggests: The method of claim 7, wherein the rotational transform Rk(p) and a translational transform Tk(p) for the joint k is determined based on [the claimed Eq.] (Le Eq. 7; Eisemann [0078] “Sparsity: only ‘few’ w.sub.ij>0; leads to simpler controls and a faster rendering process” [0099] “To sparsify the set of weights per vertex i, a bone index j should be removed from B(i) if weight w.sub.ij is small”). The same rationales to combine as set forth in the rejection of claims 1 and 6 are incorporated herein.
Claims 14-16 recite limitation(s) similar in scope to those of claims 6-8, respectively, and are rejected for the same reason(s).
Claim 8 recites limitation(s) similar in scope to those of claim 8, and is rejected for the same reason(s).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US 2022/0301262 – predict secondary motion
US 2023/0154111 – 3D reconstruction of human head
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