Robust and accurate skeletal rigging from mesh sequences
The DOI matches its Crossref record; 58 of the 58 references it cites were found in a registry or an index; 1 of the 33 sources its claims cite were checked for support.
Abstract
We introduce an example-based rigging approach to automatically generate linear blend skinning models with skeletal structure. Based on a set of example poses, our approach can output its skeleton, joint positions, linear blend skinning weights, and corresponding bone transformations. The output can be directly used to set up skeleton-based animation in various 3D modeling and animation software as well as game engines. Specifically, we formulate the solving of a linear blend skinning model with a skeleton as an optimization with joint constraints and weight smoothness regularization, and solve it using an iterative rigging algorithm that (i) alternatively updates skinning weights, joint locations, and bone transformations, and (ii) automatically prunes redundant bones that can be generated by an over-estimated bone initialization. Due to the automatic redundant bone pruning, our approach is more robust than existing example-based rigging approaches. Furthermore, in terms of rigging accuracy, even with a single set of parameters, our approach can soundly outperform state of the art methods on various types of experimental datasets including humans, quadrupled animals, and highly deformable models.
Overview
CoChat Summary
## TL;DR
The paper presents an example-based rigging method that automatically produces a skeleton-based linear blend skinning (LBS) model from a sequence of example poses. It improves robustness by over-initializing bones and pruning redundancies, and improves accuracy by iteratively updating weights, joint locations, and bone transformations with soft joint constraints.
## Key findings
- The method outputs the skeleton, joint positions, skinning weights, and bone transformations directly from example poses.
- On 9 test datasets, the paper reports that using a single parameter set, the method outperformed three state-of-the-art methods in robustness and accuracy.
- In Table 1, the reported RMSEs for the authors’ method are lower than the comparators across all listed datasets, e.g.:
- cat-poses: 0.25 vs. 0.68 / 1.04 / 0.63
- horse-poses: 0.21 vs. 0.54 / 1.24 / 0.75
- hand: 0.18 vs. 0.23 / 0.42 / 0.18
- cow: 1.52 vs. 5.41 / 5.61 / 5.58
- The paper reports that the method can rig difficult models with few frames, e.g. 9 frames produced a 28-bone skeleton for the cat model.
## Methods
- Example-based rigging pipeline with three main stages: initialization from motion-driven clustering, topology reconstruction via skinning decomposition and a minimum spanning tree, and iterative rigging with block coordinate descent.
- Input: a temporally coherent set of example poses (mesh sequence) plus a rest pose; output: skeletal structure, joint locations, skinning weights, and bone transformations.
- Main analysis: optimization of an LBS model with data fitting, weight smoothness regularization, and soft joint constraints; redundant bones are pruned during iterative updates.
## Limitations
- The paper states that the method has low computational efficiency and is suitable only for offline applications.
- The paper states that results depend on the quality of the input example poses; noise, limited motion range, and asymmetry can affect output.
- The paper states that the LBS model has limited approximation power and cannot capture some complicated nonlinear deformations.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures

![Figure 2 Examples that show two common limitations of current rigging methods: (i) an over-estimated bone initialization may generate inaccurate and redundant bones (indicated by red arrows); (ii) an inaccurate estimation of bone transformations (indicated by red arrows with ellipse) causes noticeable deformation errors when the bones are connected by joints (see the change of the legs). The examples in this figure are generated using [Hasler et al. 2010].](https://figures.cochat.ai/paper-figures/b31b6caaf34d4c0480feb3af36e4ecd2/robust-and-accurate-skeletal-rigging-from-mesh-sequences-figure-2.png)


![Figure 5 The effect of different weight smoothness regularizations. Compared to the graph Laplacian [Merry et al. 2006; Kim et al. 2010], our rigidness Laplacian regularization offers better smoothness while still preserving the global shape. Note that how the graph Laplacian over-smooths the fracture while it starts to change the global shape (indicated by red circles). Our rigidness Laplacian is robust as demonstrated by the similar results with different ω values.](https://figures.cochat.ai/paper-figures/b9eca0f860b8405aa00ed142a4709953/robust-and-accurate-skeletal-rigging-from-mesh-sequences-figure-5.png)
![Figure 6 (Left) Without joint constraints, the bone transformations generated by [Le and Deng 2012] do not always rotate around the joints. (Right) With the soft joint constraints, bones rotate more strictly around the joints. Since bone transformations are alternatively updated with joint locations, our model can converge to a local optimum with a good approximation of the input.](https://figures.cochat.ai/paper-figures/793f8e1c5263474ca9841ce3ca78bf94/robust-and-accurate-skeletal-rigging-from-mesh-sequences-figure-6.png)






![Method III [de Aguiar et al. 2008a]](https://figures.cochat.ai/paper-figures/628fe4fe9e5f4f9cacdf86cb9e5b788b/robust-and-accurate-skeletal-rigging-from-mesh-sequences-figure-13.png)



Verification
Claims the paper makes
0 Valid · 1 Not valid · 21 Not checked · 72 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“As a tradeoff, [Anguelov et al. 2004] gives a slightly larger approximation error than [Schaefer and Yuksel 2007].”
What the sources say
- Could not verifycites Anguelov et al. 2004 matched to “Recovering articulated object models from 3D range data” (2012) doi:10.5555/1036843.1036846Experimental — accuracy not yet measured
The Experimental Results (p. 7) describe the paper’s puppet and arm datasets but do not compare approximation errors with Schaefer and Yuksel 2007. A search for that comparison and for approximation error found no supporting passage in our copy. (LLM, conf=0.78)
- Not matchedcites Schaefer and Yuksel 2007
An author–year citation the paper’s reference list doesn’t settle. We don’t search these by name.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
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
“We introduce an example-based rigging approach to automatically generate linear blend skinning models with skeletal structure.”
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.
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
“Furthermore, in terms of rigging accuracy, even with a single set of parameters, our approach can soundly outperform state of the art methods on various types of experimental datasets including humans, quadrupled animals, and highly deformable models.”
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.
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
“As shown in Fig. 1, our method can robustly generate high-quality rigging models from a small set of example poses.”
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.
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
“By formulating the solving of a LBS model with skeleton as a constrained optimization, our iterative approach can obtain more accurate joint locations, bone lengths, corresponding joint rotations, as well as the reconstruction of the example poses without accumulation of fitting errors.”
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.
49 more claims
Create a free account to see all 94 claims and every source verdict.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 19
Citations
Cites
An Algorithm for Vector Quantizer Design
Linde, Y., Buzo, A., & Gray, R. (1980) · IEEE Transactions on Communications · doi:10.1109/tcom.1980.1094577 · Cited by 7,201 · cited 3×
“We apply the Linde-Buzo-Gray (LBG) algorithm [Linde et al. 1980] to cluster the vertices with similar rigid transformations.”
MethodInfluentialOn the shortest spanning subtree of a graph and the traveling salesman problem
Kruskal, J. B. (1956) · Proceedings of the American Mathematical Society · doi:10.1090/s0002-9939-1956-0078686-7 · Cited by 5,088
SCAPE: shape completion and animation of people
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., & Davis, J. (2005) · ACM Transactions on Graphics · doi:10.1145/1073204.1073207 · Cited by 1,489
A discussion of the solution for the best rotation to relate two sets of vectors
Kabsch, W. (1978) · Acta Crystallographica Section A · doi:10.1107/s0567739478001680 · Cited by 1,151 · cited 1×
“(6a) is to combine the solution proposed by Le and Deng [2012] with the solution to the Weighted Absolute Orientation problem [Kabsch 1978].”
MethodOn the Shortest Spanning Subtree of a Graph and the Traveling Salesman Problem
Kruskal, J. B. (1956) · Proceedings of the American Mathematical Society · doi:10.2307/2033241 · Cited by 1,117
Deformation transfer for triangle meshes
Sumner, R. W., & Popović, J. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015736 · Cited by 1,052
Articulated mesh animation from multi-view silhouettes
Vlasic, D., Baran, I., Matusik, W., & Popović, J. (2008) · ACM Transactions on Graphics · doi:10.1145/1360612.1360696 · Cited by 610
Performance capture from sparse multi-view video
de Aguiar, E., Stoll, C., Theobalt, C., Ahmed, N., Seidel, H.-P., & Thrun, S. (2008) · ACM Transactions on Graphics · doi:10.1145/1360612.1360697 · Cited by 535
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 · cited 2×
“Many automatic methods have been proposed to generate the skinning weights from a static 3D model [Baran and Popovi´c 2007; Jacobson et al. 2011].”
Method
Research works printed but not linked: 1
- DE AGUIAR, E., THEOBALT, C., THRUN, S., AND SEIDEL, H.-P. 2008. Automatic conversion of mesh animations into skeletonbased animations. Comput. Graph. Forum 27 , 2 (4), 389-397.
Cited by
Items 101–115 of 115
A linear blending scheme for rigid and non-rigid deformations
Liu, G., & Anjyo, K. (2015) · SIGGRAPH Asia Technical Briefs · doi:10.1145/2820903.2820912
“In the second term, we use rigidness Laplacian regularization (RLR) Lîi [Le and Deng 2014] to smooth weights, where î refers to 1-ring neighbors of the i vertex.”
MethodBowyer, S. A., & y Baena, F. R. (2016) · doi:10.1145/2993369.2993392
Position-based Skin Deformations for Interactive Character Animation
Rumman, N. A. (2016) · Eurographics · doi:10.2312/2631656
Affect-Preserving Visual Privacy Protection
Xu, W. (2018) · UKnowledge (University of Kentucky) · doi:10.13023/etd.2018.303
“Similar to [101][102], we find the solution to the Weighted Absolute Orientation problem”
MethodLearning 3D Deformation of Animals from 2D ImagesPreprint
Kanazawa, A., Kovalsky, S. Z., Basri, R., et al. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1507.07646
Locality-Aware Skinning Decomposition Using Model-Dependent Mesh Clustering
Narita, F., & Mukai, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-61864-3_5
Analysis and Exploration of Large 3D Shape Databases
Chen, X. (2021) · University of Groningen research database (University of Groningen / Centre for Information Technology) · doi:10.33612/diss.172474105
Kallmann, M. (2016) · CRC Press eBooks · doi:10.1201/9781315370071-13
TMD: Transformed Mesh Decoder for Mesh Animation
Fasogbon, P., Zhang, H., Cricri, F., Tavakoli, H. R., & Aksu, E. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956209
“Currently, the fundamental techniques to accomplish mesh animation from pose are based on the process of “rigging” and “skinning” [1], [2].”
BackgroundA Novel Method of Skeletonization of Complex Shapes Based on Bisectors
Saidou, N., Zineddine, M., & Rhazzaf, M. (2024) · Computing Open · doi:10.1142/s2972370123500083
Hierarchical Spherical Cross‐Parameterization for Deforming Characters
Cao, L., & Peng, C. Y. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15197
ASMR: Adaptive Skeleton‐Mesh Rigging and Skinning via 2D Generative Prior
Hong, S., Choi, S., Kim, C., Cha, S., & Noh, J. (2025) · Computer Graphics Forum · doi:10.1111/cgf.70052 · Cited by 2
“Dual Quater-nion Skinning (DQS) [Hej04,KCŽO07,LD14] better preserves rotational properties, leading to smoother deformations.”
Rig My Ride: Automatic Rigging of Physics-based Vehicles for Games
Katz, M., Kry, P. G., & Andrews, S. (2025) · Proceedings of the ACM on Computer Graphics and Interactive Techniques · doi:10.1145/3747861
“Other work has similarly inferred rig parameters from mesh animation sequences [Le and Deng 2014], however this requirement does not apply to our target use case.”
Xiong, Y., Chen, Y., Shi, Y., Hu, Z., & Ni, B. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754757 · Cited by 1
“To address this, early methods [1, 11, 28, 38, 67, 73] automate skeleton prediction, while others [3, 4, 9, 26, 27, 31, 41, 43, 45] estimate skinning weights given a predefined skeleton.”
High-Fidelity Garment Animation via Adaptive Bone Density Control
Cheng, Y., Weng, D., Zhao, Z., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4966-5_11
Metadata
- Authors
- Le, B. H., & Deng, Z.
- Affiliations
- University of Houston (US)
- ORCID
- Deng, Zhigang
- Venue
- ACM Transactions on Graphics
- Published
- 2014-07-27
- Volume
- 33
- Issue
- 4
- Pages
- 1-10
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W2152005648
- Cited by
- 111
- References
- 46
- Citations by year
- 2026: 2 · 2025: 8 · 2024: 7 · 2023: 9 · 2022: 2 · 2021: 15 · 2020: 11 · 2019: 12 · 2018: 12 · 2017: 2 · 2016: 19 · 2015: 10 · 2014: 2
- FWCI
- 9.98
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Graphics (publishedVersion)
- Funders
- National Institutes of Health
- National Natural Science Foundation of China (61328204)
- Division of Information and Intelligent Systems
- 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
- linear blend skinning, skeleton estimation, joint position estimation, skeleton-based animation, 3D character animation
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.