Learning skeletal articulations with neural blend shapes
The DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index; 5 of the 16 sources its claims cite were checked for support.
Abstract
Animating a newly designed character using motion capture (mocap) data is a long standing problem in computer animation. A key consideration is the skeletal structure that should correspond to the available mocap data, and the shape deformation in the joint regions, which often requires a tailored, pose-specific refinement. In this work, we develop a neural technique for articulating 3D characters using enveloping with a pre-defined skeletal structure which produces high quality pose dependent deformations. Our framework learns to rig and skin characters with the same articulation structure ( e.g. , bipeds or quadrupeds), and builds the desired skeleton hierarchy into the network architecture. Furthermore , we propose neural blend shapes - a set of corrective pose-dependent shapes which improve the deformation quality in the joint regions in order to address the notorious artifacts resulting from standard rigging and skinning. Our system estimates neural blend shapes for input meshes with arbitrary connectivity, as well as weighting coefficients which are conditioned on the input joint rotations. Unlike recent deep learning techniques which supervise the network with ground-truth rigging and skinning parameters, our approach does not assume that the training data has a specific underlying deformation model. Instead, during training, the network observes deformed shapes and learns to infer the corresponding rig, skin and blend shapes using indirect supervision. During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists. Conforming to standard skeletal animation models enables direct plug-and-play in standard animation software, as well as game engines.
Overview
CoChat Summary
TL;DR
The paper presents a neural framework that rigs and skins a character mesh with a prescribed skeleton hierarchy and predicts neural blend shapes for pose-dependent corrective deformation, using indirect supervision from articulated vertex positions. It reports improved rigging and skinning accuracy over Pinocchio and RigNet and demonstrates generalization to unseen characters with arbitrary mesh connectivity.
Key findings
- Rigging accuracy: Table 1 reports CD-J2J / CD-J2B / CD-B2B of 0.012 / 0.007 / 0.004 for the proposed method, versus 0.194 / 0.084 / 0.009 for RigNet and 0.474 / 0.164 / 0.025 for Pinocchio.
- Skinning and deformation: Table 2 reports skinning weight L1 error 2.56 for the proposed method versus 23.1 for Pinocchio; average distance 0.011 versus 0.27; max distance 1.68 versus 20.3.
- Ablation: Table 3 reports L2 error 0.011 with all components, 0.024 with envelope only, 0.66 without mesh augmentation, and 0.23 without garment augmentation; the paper states mesh augmentation has the most quantitative impact, while neural blend shapes are extremely important for visual quality.
- The paper reports that 9 blend shapes were enough for high-quality pose-dependent deformations, and that indirect supervision converges slower than direct supervision (80,000 vs. 45,000 iterations to reach Lv = 0.024) but with comparable deformation quality.
Methods
- The framework has two branches: an envelope deformation branch that predicts skeletal offsets O and skinning weights W using MeshCNN and skeleton-aware operators, and a residual deformation branch that predicts N blend shapes plus pose-dependent blending coefficients conditioned on joint rotations, with a mask for localization.
- Training uses the SMPL dataset (10 shape blend shapes and 207 pose-dependent blend shapes) and the Multi Garment Network dataset (96 clothed humans; 80 for training, 16 for testing), with mesh connectivity augmentation (edge collapse, split, flip) and garment augmentation. Test groups are 5 animator-created biped characters, 30 random SMPL characters, and 16 held-out clothed characters; Mixamo characters are used to test generalization.
- Training is implemented in PyTorch with a two-stage coarse-to-fine approach and Adam, taking about 3 days; supervision is indirect, using an L2 loss on articulated vertex positions rather than ground-truth rigging or skinning parameters.
Limitations
- Stated: the output is bounded by the quality of deformations in the training dataset; most results are trained using SMPL-like models, and artifacts can appear where the selected model was not trained sufficiently. Changing the prescribed skeleton structure requires retraining the entire network.
- Stated: the network assumes a consistent upright and front-facing orientation and a T-pose input; non-manifold edges or vertices should be deleted, and extreme polygon soup may require remeshing or tetrahedralization.
- Evident from the text: the system is trained on characters with the same articulation structure (e.g., bipeds) and evaluated on human/humanoid characters, so generalization to other articulation structures or arbitrary skeleton hierarchies is not quantitatively demonstrated.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
3 Valid · 3 Not valid · 7 Not checked · 64 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The latter requires motion retargeting between two skeletons with different, unseen, structures, which is still an open problem [Gleicher 1998; Aberman et al. 2020].”
What the sources say
- Not checked — no full text of the sourcecites Gleicher 1998 source
- Supportedcites Aberman et al. 2020 source
Section 6.3 (p. 11) says the authors train a special model for each character with a unique skeletal structure, supporting the distinction between retargeting to a trained structure and to an unseen one. The Overview (p. 4) likewise describes decoding with a decoder trained for the target domain. The paper demonstrates retargeting across different trained, homeomorphic structures; it does not present retargeting to an unseen structure as solved. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Yet, animating an arbitrary skeleton rig using mocap data is not directly possible due to incompatibility in the skeletal structure.”
What the sources say
- Not checked — no full text of the sourcecites Gleicher 1998 source
- Supportedcites Aberman et al. 2020 source
The Introduction (p. 1) says captured skeletons can differ in structure and joint count, making motion retargeting necessary across setups. The discussion on p. 2 adds that transferring motion between differently structured skeletons cannot be done automatically by the approaches it describes and requires manual correspondences. (LLM, conf=0.91)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“Our framework produces pose-dependent displacements that result in high quality deformations, especially in the joint regions.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“During inference, we demonstrate that our network generalizes to unseen characters with arbitrary mesh connectivity, including unrigged characters built by 3D artists.”
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Our predicted envelope deformation produces favorable results, compared to LBS.”
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
37 more claims
Create a free account to see all 77 claims and every source verdict.
- It may state two separate claims as one. 30
- Probably not a substantial claim. 7
- The quote only partly states this claim. 1
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
(1993) · doi:10.1109/cvpr.1993 · Cited by 17,667
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R. Q., Su, H., Kaichun, M., & Guibas, L. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.16 · Cited by 9,237
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., & J, B. M. (2015) · ACM Transactions on Graphics · doi:10.1145/2816795.2818013 · Cited by 3,734 · cited 9×
“…based on projections and heat diffusion [Baran and Popović 2007; Wareham and Lasenby 2008], bounded biharmonic energy [Jacobson et al. 2011], geodesic voxel binding [Dionne and de Lasa 2013], and physics-inspired approaches [Kavan and Sorkine 2012 et al. 2000; Kry et al. 2002; Loper et al. 2015].”
BackgroundMethodInfluentialHoppe, H. (1996) · Proceedings of the 23rd annual conference on Computer graphics and interactive techniques · doi:10.1145/237170.237216 · Cited by 2,817 · cited 1×
“In order to enrich the set of samples that the network is trained on and to enhance its robustness to different mesh connectivity, we augment the data samples by applying three topological operators on edges: collapse, split and flip [Hoppe 1996; Botsch et al. 2010].”
MethodRetargetting motion to new characters
Gleicher, M. (1998) · Proceedings of the 25th annual conference on Computer graphics and interactive techniques - SIGGRAPH '98 · doi:10.1145/280814.280820 · Cited by 854 · cited 1×
“The latter requires motion retargeting between two skeletons with different, unseen, structures, which is still an open problem [Gleicher 1998; Aberman et al. 2020].”
BackgroundPose space deformation: a unified approach to shape interpolation and skeleton-driven deformation
Lewis, J. P., Cordner, M., & Fong, N. (2000) · Proceedings of the 27th annual conference on Computer graphics and interactive techniques - SIGGRAPH '00 · doi:10.1145/344779.344862 · Cited by 853
Botsch, M., Kobbelt, L., Pauly, M., Alliez, P., & Levy, B. (2010) · A K Peters/CRC Press eBooks · doi:10.1201/b10688 · Cited by 814
Duke, D., & Scopigno, R. (2003) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2003.00715.x · Cited by 769
MeshCNN: a network with an edge
Hanocka, R., Hertz, A., Fish, N., Giryes, R., Fleishman, S., & Cohen-Or, D. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322959 · Cited by 742
Self-citationMean value coordinates for closed triangular meshes
Ju, T., Schaefer, S., & Warren, J. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073229 · Cited by 564
Skeleton extraction by mesh contraction
Au, O. K.-C., Tai, C.-L., Chu, H.-K., Cohen-Or, D., & Lee, T.-Y. (2008) · ACM Transactions on Graphics · doi:10.1145/1360612.1360643 · Cited by 521
Automatic rigging and animation of 3D characters
Baran, I., & Popović, J. (2007) · ACM SIGGRAPH 2007 papers · doi:10.1145/1275808.1276467 · Cited by 495
Automatic rigging and animation of 3D characters
Baran, I., & Popović, J. (2007) · ACM Transactions on Graphics · doi:10.1145/1276377.1276467 · Cited by 455
Multi-Garment Net: Learning to Dress 3D People From Images
Bhatnagar, B., Tiwari, G., Theobalt, C., & Pons-Moll, G. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00552 · Cited by 439 · cited 3×
“Most of the results shown in this paper are trained using examples generated by SMPL-like models [Loper et al. 2015; Bhatnagar et al. 2019].”
MethodHarmonic coordinates for character articulation
Joshi, P., Meyer, M., DeRose, T., Green, B., & Sanocki, T. (2007) · ACM Transactions on Graphics · doi:10.1145/1276377.1276466 · Cited by 401
Bounded biharmonic weights for real-time deformation
Jacobson, A., Baran, I., Popović, J., & Sorkine, O. (2011) · ACM Transactions on Graphics · doi:10.1145/2010324.1964973 · Cited by 334
Point Cloud Skeletons via Laplacian Based Contraction
Cao, J., Tagliasacchi, A., Olson, M., Zhang, H., & Su, Z. (2010) · 2010 Shape Modeling International Conference · doi:10.1109/smi.2010.25 · Cited by 313
Sloan, P.-P. J., Rose, C. F., & Cohen, M. F. (2001) · Proceedings of the 2001 symposium on Interactive 3D graphics · doi:10.1145/364338.364382 · Cited by 273
Skinning with dual quaternions
Kavan, L., Collins, S., Žára, J., & O'Sullivan, C. (2007) · Proceedings of the 2007 symposium on Interactive 3D graphics and games · doi:10.1145/1230100.1230107 · Cited by 270 · cited 4×
“Existing works develop improved techniques to overcome such shortcomings, such as dual quaternion skinning [Hejl 2004; Kavan et al. 2007; Le and Hodgins 2016], spherical based skinning [Kavan and Žára 2005], multi-linear techniques [Wang and Phillips 2002; Merry et al.”
BackgroundMethodInfluentialEigenSkin: real time large deformation character skinning in hardware
Kry, P. G., James, D. L., & Pai, D. K. (2002) · Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation · doi:10.1145/545261.545286 · Cited by 267 · cited 4×
“2007], statistical models [Kry et al. 2002; Loper et al. 2015], or a compact sparse format [Seo et al.”
BackgroundMethodInfluentialSymposium on geometry processing
(2006) · Computers & Graphics · doi:10.1016/j.cag.2006.01.014 · Cited by 264
Sumner, R. W., Zwicker, M., Gotsman, C., & Popović, J. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073218 · Cited by 263
Bounded biharmonic weights for real-time deformation
Jacobson, A., Baran, I., Popović, J., & Sorkine, O. (2011) · ACM SIGGRAPH 2011 papers · doi:10.1145/1964921.1964973 · Cited by 258
STAR: Sparse Trained Articulated Human Body Regressor
Osman, A. A. A., Bolkart, T., & Black, M. J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58539-6_36 · Cited by 252
Point2Mesh: a self-prior for deformable meshes
Hanocka, R., Metzer, G., Giryes, R., & Cohen-Or, D. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392415 · Cited by 242
Self-citationSkeleton-aware networks for deep motion retargeting
Aberman, K., Li, P., Lischinski, D., Sorkine-Hornung, O., Cohen-Or, D., & Chen, B. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392462 · Cited by 230
Self-citationMulti-weight enveloping: least-squares approximation techniques for skin animation
Wang, X. C., & Phillips, C. (2002) · Proceedings of the 2002 ACM SIGGRAPH/Eurographics symposium on Computer animation · doi:10.1145/545261.545283 · Cited by 196
Spherical blend skinning: a real-time deformation of articulated models
Kavan, L., & Žára, J. (2005) · Proceedings of the 2005 symposium on Interactive 3D graphics and games · doi:10.1145/1053427.1053429 · Cited by 184
Fast tetrahedral meshing in the wild
Hu, Y., Schneider, T., Wang, B., Zorin, D., & Panozzo, D. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392385 · Cited by 181 · cited 1×
“In general, there should be a meaningful shape surface to propagate the deep mesh features; so in the case of an extreme polygon soup some form of remeshing [research 2020] or tetrahedralization [Hu et al. 2020] can be employed.”
BackgroundNeural Rendering and Reenactment of Human Actor Videos
Liu, L., Xu, W., Zollhöfer, M., Kim, H., Bernard, F., Habermann, M., Wang, W., & Theobalt, C. (2019) · ACM Transactions on Graphics · doi:10.1145/3333002 · Cited by 163
Self-citationContext‐Aware Skeletal Shape Deformation
Weber, O., Sorkine, O., Lipman, Y., & Gotsman, C. (2007) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2007.01048.x · Cited by 148
Neural Cages for Detail-Preserving 3D Deformations
Yifan, W., Aigerman, N., Kim, V. G., Chaudhuri, S., & Sorkine-Hornung, O. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00015 · Cited by 132 · cited 1×
“…spherical based skinning [Kavan and Žára 2005], multi-linear techniques [Wang and Phillips 2002; Merry et al. 2006], and approaches with additional deformers or cages [Ju et al. 2005; Joshi et al. 2007; Jacobson et al. 2011; Kavan and Sorkine 2012; Mukai and Kuriyama 2016; Yifan et al. 2020].”
BackgroundSelf-citationXu, Z., Zhou, Y., Kalogerakis, E., Landreth, C., & Singh, K. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392379 · Cited by 126
Automatic Conversion of Mesh Animations into Skeleton‐based Animations
De Aguiar, E., Theobalt, C., Thrun, S., & Seidel, H. (2008) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2008.01136.x · Cited by 113
Robust and accurate skeletal rigging from mesh sequences
Le, B. H., & Deng, Z. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601161 · Cited by 111
Hahn, F., Martin, S., Thomaszewski, B., Sumner, R., Coros, S., & Gross, M. (2012) · ACM Transactions on Graphics · doi:10.1145/2185520.2185568 · Cited by 109
Example‐Driven Deformations Based on Discrete Shells
Fröhlich, S., & Botsch, M. (2011) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2011.01974.x · Cited by 107
Elasticity-inspired deformers for character articulation
Kavan, L., & Sorkine, O. (2012) · ACM Transactions on Graphics · doi:10.1145/2366145.2366215 · Cited by 103 · cited 2×
“…spherical based skinning [Kavan and Žára 2005], multi-linear techniques [Wang and Phillips 2002; Merry et al. 2006], and approaches with additional deformers or cages [Ju et al. 2005; Joshi et al. 2007; Jacobson et al. 2011; Kavan and Sorkine 2012; Mukai and Kuriyama 2016; Yifan et al. 2020].”
BackgroundAnimation space: A truly linear framework for character animation
Merry, B., Marais, P., & Gain, J. (2006) · ACM Transactions on Graphics · doi:10.1145/1183287.1183294 · Cited by 91 · cited 2×
“…2004; Kavan et al. 2007; Le and Hodgins 2016], spherical based skinning [Kavan and Žára 2005], multi-linear techniques [Wang and Phillips 2002; Merry et al. 2006], and approaches with additional deformers or cages [Ju et al. 2005; Joshi et al. 2007; Jacobson et al. 2011; Kavan and Sorkine…”
Background(2007) · doi:10.5555/1281991.1282013 · Cited by 88
James, D. L., & Twigg, C. D. (2005) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/1186822.1073206 · Cited by 76
Pose Space Deformation: A Unified Approach to Shape Interpolation and Skeleton-Driven Deformation
Lewis, J. P., Cordner, M., & Fong, N. (2023) · Seminal Graphics Papers: Pushing the Boundaries, Volume 2 · doi:10.1145/3596711.3596796 · Cited by 76
Proceedings on Graphics interface '88
Peachey, D. (1989) · Graphics Interface · Cited by 68
NeuroSkinning: automatic skin binding for production characters with deep graph networks
Liu, L., Zheng, Y., Tang, D., Yuan, Y., Fan, C., & Zhou, K. (2019) · ACM Transactions on Graphics · doi:10.1145/3306346.3322969 · Cited by 67
Self-citationLearning skeletons for shape and pose
Hasler, N., Thormählen, T., Rosenhahn, B., & Seidel, H.-P. (2010) · Proceedings of the 2010 ACM SIGGRAPH symposium on Interactive 3D Graphics and Games · doi:10.1145/1730804.1730809 · Cited by 66
Geodesic voxel binding for production character meshes
Dionne, O., & de Lasa, M. (2013) · Proceedings of the 12th ACM SIGGRAPH/Eurographics Symposium on Computer Animation · doi:10.1145/2485895.2485919 · Cited by 66
Fast and deep deformation approximations
Bailey, S. W., Otte, D., Dilorenzo, P., & O'Brien, J. F. (2018) · ACM Transactions on Graphics · doi:10.1145/3197517.3201300 · Cited by 61
Real-time skeletal skinning with optimized centers of rotation
Le, B. H., & Hodgins, J. K. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925959 · Cited by 60
Fast and deep facial deformations
Bailey, S. W., Omens, D., DiLorenzo, P. C., & O’Brien, J. F. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392397 · Cited by 49 · cited 2×
“Neural networks can also be trained to convert high-level user con-trol into rig parameters [Bailey et al. 2020] to enable user-friendly editing of mesh deformation.”
BackgroundAutomatically Rigging Multi‐component Characters
Bharaj, G., Thormählen, T., Seidel, H., & Theobalt, C. (2012) · Computer Graphics Forum · doi:10.1111/j.1467-8659.2012.03034.x · Cited by 44
Bone Glow: An Improved Method for the Assignment of Weights for Mesh Deformation
Wareham, R., & Lasenby, J. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-70517-8_7 · Cited by 40 · cited 1×
“Previous research exploits methods based on projections and heat diffusion [Baran and Popović 2007; Wareham and Lasenby 2008], bounded biharmonic energy [Jacobson et al. 2011], geodesic voxel binding [Dionne and de Lasa 2013], and physics-inspired approaches [Kavan and Sorkine 2012].”
MethodCompression and direct manipulation of complex blendshape models
Seo, J., Irving, G., Lewis, J. P., & Noh, J. (2011) · ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia (SIGGRAPH Asia) · doi:10.1145/2024156.2024198 · Cited by 39
Proceedings of the 2005 symposium on Interactive 3D graphics and games
(2005) · doi:10.1145/1053427 · Cited by 37
Efficient dynamic skinning with low-rank helper bone controllers
Mukai, T., & Kuriyama, S. (2016) · ACM Transactions on Graphics · doi:10.1145/2897824.2925905 · Cited by 31 · cited 1×
“…spherical based skinning [Kavan and Žára 2005], multi-linear techniques [Wang and Phillips 2002; Merry et al. 2006], and approaches with additional deformers or cages [Ju et al. 2005; Joshi et al. 2007; Jacobson et al. 2011; Kavan and Sorkine 2012; Mukai and Kuriyama 2016; Yifan et al. 2020].”
BackgroundZhang, J. E., Bang, S., Levin, D. I. W., et al. (2020) · ACM Transactions on Graphics · doi:10.1145/3414685.3417819 · Cited by 26 · cited 1×
“Blending coefficients can also be updated in a dynamic simulation to generate secondary effects [Hahn et al. 2012; Zhang et al. 2020].”
BackgroundFrankenrigs: building character rigs from multiple sources
Miller, C., Arıkan, O., & Fussell, D. (2010) · ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D) · doi:10.1145/1730804.1730810 · Cited by 24 · cited 2×
“Miller et al. [2010] later demonstrate a system that automatically rigs an input mesh by combining parts from a number of templates.”
BackgroundMethodFrankenrigs: Building Character Rigs from Multiple Sources
Miller, C., Arıkan, O., & Fussell, D. S. (2011) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2011.39 · Cited by 17
Kry, P. G., James, D. L., & Pai, D. K. (2002) · doi:10.1145/545282.545286 · Cited by 17
Articulated Motion and Deformable Objects
Hutchison, D., Weikum, G., Vardi, M. Y., et al. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-70517-8 · Cited by 16
Rig it Right! Maya Animation Rigging Concepts
O'Hailey, T. (2013) · Routledge eBooks · doi:10.4324/9780240820910 · Cited by 5
Rig it Right! Maya Animation Rigging Concepts
O'Hailey, T. (2018) · Routledge eBooks · doi:10.1201/9780429461453 · Cited by 5
Accurate Face Rig Approximation with Deep Differential Subspace Reconstruction
Song, S. L., Shi, W., & Reed, M. (2020) · arXiv · doi:10.48550/arxiv.2006.01746
Research works printed but not linked: 3
- 10.1111/j.1467-8659.2012.03034.x_eprint · doi:10.1111/j.1467-8659.2012.03034.x_eprint
- Jim Hejl . 2004 . Hardware skinning with quaternions . Game Programming Gems 4 (2004), 487 -- 495 . Jim Hejl. 2004. Hardware skinning with quaternions. Game Programming Gems 4 (2004), 487--495.
- Tianxing Li , Rui Shi , and Takashi Kanai . 2020 . DenseGATs: A Graph-Attention-Based Network for Nonlinear Character Deformation. In Symposium on Interactive 3D Graphics and Games. 1--9. Tianxing Li, Rui Shi, and Takashi Kanai. 2020. DenseGATs: A Graph-Attention-Based Network for Nonlinear Character Deformation. In Symposium on Interactive 3D Graphics and Games. 1--9.
Cited by
Yan, C., Sun, Y. M., Bao, Q., et al. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547743
“Then we employ a MeshCNN from NBS [3] to extract the”
MethodNeural network for automatic skinning weight painting using SDF
Seol, H., & Kwon, T. (2023) · Journal of the Korea Computer Graphics Society · doi:10.15701/kcgs.2023.29.4.17
Lps: Learning Pose Transfer from Point Clouds to Stylized 3d CharactersPreprint
Yan, J., Liu, J., Tang, J., & Wu, G. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4900421
Qin, J. (2024) · IEEE International Conference on Sensors, Electronics and Computer Engineering (ICSECE) · doi:10.1109/icsece61636.2024.10729343
“By inserting additional bones and manually adjusting skinning weights, LBS can also generate soft body effects, but this method not only requires a lot of time investment but also has high requirements for artists [4,5].”
BackgroundSkin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging
Zhang, J.-P., Pu, C.-F., Guo, M.-H., Cao, Y.-P., & Hu, S.-M. (2026) · arXiv · doi:10.48550/arxiv.2602.04805
“Similarly, NeuroSkinning [Liu et al. 2019] utilizes graph convolu-tions with multi-head attention, while Neural Blend Shapes [Li et al. 2021] employs MeshCNN [Hanocka et al. 2019] for local feature extraction.”
Metadata
- Authors
- Li, P., Aberman, K., Hanocka, R., Liu, L., Sorkine-Hornung, O., & Chen, B.
- Affiliations
- Peking University (CN)
- Google (United States) (US)
- Tel Aviv University (IL)
- ETH Zurich
- Venue
- ACM Transactions on Graphics
- Published
- 2021-07-19
- Volume
- 40
- Issue
- 4
- Pages
- 1-15
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W4235221956
- Cited by
- 4
- References
- 47
- Citations by year
- 2024: 2 · 2023: 1 · 2022: 1
- FWCI
- 0.57
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Graphics (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Human Motion and Animation
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Keywords
- skeletal animation, character deformation, artificial neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.