RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
Open accessThe DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index; 3 of the 11 sources its claims cite were checked for support.
Abstract
We present RigAnything, a novel autoregressive transformer-based model, which makes 3D assets rig-ready by probabilistically generating joints and skeleton topologies and assigning skinning weights in a template-free manner. Unlike most existing auto-rigging methods, which rely on predefined skeleton templates and are limited to specific categories like humanoid, RigAnything approaches the rigging problem in an autoregressive manner, iteratively predicting the next joint based on the global input shape and the previous prediction.
Overview
CoChat Summary
TL;DR
RigAnything is a template-free autoregressive transformer that generates skeleton joints/topologies and skinning weights for diverse 3D assets by serializing skeletons in BFS order and using diffusion for continuous joint positions. It reports state-of-the-art skeleton and skinning metrics and completes rigging in about 2 seconds per shape on an A100, versus about 120 seconds for RigNet.
Key findings
- On the RigNet + Objaverse dataset, RigAnything improves skeleton prediction over RigNet: IoU 0.768 vs. 0.456, precision 0.789 vs. 0.424, recall 0.766 vs. 0.591, CD-J2J 0.034 vs. 0.048, CD-J2B 0.035 vs. 0.042, and CD-B2B 0.020 vs. 0.030.
- On the humanoid subset, it reports IoU 0.886 vs. TARig 0.603 and NBS 0.337, with CD-J2J 0.030 vs. 0.100 and 0.124, respectively.
- Connectivity prediction improves to 0.965 classification accuracy vs. RigNet’s 0.358, with edit distance 2.150 vs. 12.663 and CD-B2B 0.001 vs. 0.017.
- Skinning prediction achieves precision 0.825 vs. RigNet’s 0.755 and average L1 0.432 vs. 0.485, though recall is 0.798 vs. 0.828. Ablations show removing joint diffusion drops skeleton IoU to 0.308 from 0.765, and removing normals or pose augmentation lowers IoU to 0.559 and 0.741, respectively.
Methods
- The model serializes a tree skeleton in breadth-first search order as a sequence of 3D joint positions and parent indices, then autoregressively predicts the next joint with a transformer using hybrid attention: shape tokens use full self-attention, while skeleton tokens attend to shape tokens and use causal attention among themselves.
- Joint positions are sampled with a diffusion module rather than discrete prediction; connectivity and skinning weights are predicted by separate modules, and the whole model is trained end-to-end with combined joint diffusion, connectivity, and skinning losses.
- Training uses the RigNet dataset (2,354 models) plus a filtered Objaverse subset; the abstract reports 9,686 high-quality rigged shapes, Sec. 4.2 reports 12,040 after filtering, and Table 2 totals 9,388 categorized shapes. Inputs are 1024-point clouds with normals, max 64 joints, and online pose augmentation with random joint perturbations up to 45 degrees.
Limitations
- The paper states that the method does not allow control over rig level of detail, relies solely on geometry which can be ambiguous, and does not account for motion styles such as material-influenced skinning; dynamic data are scarce for addressing this.
- Evident from the text: RigNet comparisons are conducted on rest-posed objects because RigNet supports only rest poses, so arbitrary-pose performance is not directly benchmarked against RigNet.
- Evident from the text: the reported Objaverse filtered counts differ across the abstract, Sec. 4.2, and Table 2, which complicates exact dataset reproducibility.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
1 Valid · 5 Not valid · 4 Not checked · 74 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“most autoregressive models are traditionally designed for discrete outputs, making them less effective for continuous-valued tasks.”
What the sources say
- Could not verifycites Brown et al. 2020 sourceExperimental — accuracy not yet measured
Our copy of the GPT-3 paper contains no passage about autoregressive models being designed for discrete outputs or being weak at continuous-valued tasks; searches for 'discrete outputs / continuous-valued tasks', 'regression continuous output', and 'autoregressive discrete tokens continuous domain' returned nothing on point. The Limitations discussion (Section 5, p. 33) attributes the costs of the autoregressive choice to lack of bidirectionality ('our design decision comes at the cost of potentially worse performance on tasks which empirically benefit from bidirectionality') and to the token-equal pretraining objective, and Section 7 (p. 40) notes they 'continue to focus on pure autoregressive language models' for in-context learning and implementation simplicity — none of which addresses discrete versus continuous output spaces. Since our copy does not speak to the claim's point, it can neither confirm nor contradict it. (LLM, conf=0.70)
- Not matchedcites Radford et al. 2019
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Waswani et al. 2017
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Extensive experiments demonstrate that RigAnything achieves state-of-the-art performance in the auto-rigging task”
boosted- 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
“achieving greater generalizability and robustness for diverse object types in a feed-forward manner.”
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 reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“surpassing prior methods in quality, robustness, generalizability, and efficiency”
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.
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
“RigAnything demonstrates state-of-the-art performance across diverse object types, including humanoids, quadrupeds, marine creatures, insects, and many more”
boosted- 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.
42 more claims
Create a free account to see all 84 claims and every source verdict.
- It may state two separate claims as one. 17
- The quote only partly states this claim. 1
- Probably not a substantial claim. 22
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“prior template-free rigging methods Xu et al. [2020], Song et al. [2025b,a], Liu et al. [2025], Deng et al. [2025], Sun et al. [2025b], Zhang et al. [2025], Guo et al. [2025a] typically generate structural skeletons only. Their output joints are either unlabeled or assigned generic identifiers such as Joint1 or Bone003”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Liu et al. [2025]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 1 Introduction · p. 2
“We rigorously filter the Objaverse dataset and select 9686 high-quality rigged shapes, which enrich the dataset for research in this direction.”
§ 4.2 Dataset · p. 7
“Table 2. Category statistics of the filtered Objaverse dataset. | | Number | |------------------|----------| | Humanoid/Bipedal | 7459 | | Quadruped | 543 | | Insectoid | 129 | | Avian | 176 | | Marine | 251 | | Other | 830 | | Total | 9388 |”
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ 4.2 Dataset · p. 7
“After filtering, we obtain a refined set of 12,040 shapes with reliable rigging information.”
§ 4.2 Dataset · p. 7
“Table 2. Category statistics of the filtered Objaverse dataset. | | Number | |------------------|----------| | Humanoid/Bipedal | 7459 | | Quadruped | 543 | | Insectoid | 129 | | Avian | 176 | | Marine | 251 | | Other | 830 | | Total | 9388 |”
Citations
Cites
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01268 · Cited by 2,514 · cited 1×
“Autoregressive models are a powerful class of probabilistic models widely applied across domains such as natural language processing [Achiam et al. 2023; Brown et al. 2020; Radford et al. 2019] and computer vision [Chen et al. 2020; Esser et al. 2021; Li et al. 2024; Parmar et al. 2018].”
Taming Transformers for High-Resolution Image Synthesis
Esser, P., Rombach, R., & Ommer, B. (2020) · arXiv · doi:10.48550/arxiv.2012.09841 · Cited by 2,514
Scalable Diffusion Models with Transformers
Peebles, W., & Xie, S. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00387 · Cited by 2,284 · cited 1×
“The denoising MLP is conditioned on the transformer-outputted joint tokens, where these tokens are incorporated into the noise scheduler’s time embedding through AdaLN [Peebles and Xie 2023] within the Layer Normalization layers.”
Scalable Diffusion Models with Transformers
Peebles, W., & Xie, S. (2022) · arXiv · doi:10.48550/arxiv.2212.09748 · Cited by 2,284
Improved Denoising Diffusion Probabilistic Models
Nichol, A., & Dhariwal, P. (2021) · arXiv · doi:10.48550/arxiv.2102.09672 · Cited by 1,550 · cited 2×
“The joint diffusion process follows [Li et al. 2024; Nichol and Dhariwal 2021], which has a cosine noise scheduler with 1000 training steps and 50 resampling steps during inference.”
Parmar, N., Vaswani, A., Uszkoreit, J., Kaiser, Ł., Shazeer, N., Ku, A., & Tran, D. (2018) · arXiv · doi:10.48550/arxiv.1802.05751 · Cited by 1,085
Shap-E: Generating Conditional 3D Implicit FunctionsPreprint
Jun, H., & Nichol, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2305.02463 · Cited by 879
Zero-1-to-3: Zero-shot One Image to 3D Object
Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00853 · Cited by 841
Research works printed but not linked: 5
- Mark Chen, Alec Radford, Rewon Child, Jeffrey Wu, Heewoo Jun, David Luan, and Ilya Sutskever. 2020. Generative pretraining from pixels. In International conference on machine learning. PMLR, 1691–1703.
- Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840–6851.
- Peizhuo Li, Kfir Aberman, Rana Hanocka, Libin Liu, Olga Sorkine-Hornung, and Baoquan Chen. 2021. Learning skeletal articulations with neural blend shapes. ACM Transactions on Graphics (TOG) (2021).
- Jing Ma and Dongliang Zhang. 2023. TARig: Adaptive template-aware neural rigging for humanoid characters. Computers & Graphics (2023).
- A Waswani N Shazeer N Parmar J Uszkoreit L Jones A Gomez L Kaiser and I Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems.
Cited by
Zhang, H., Xu, H., Feng, C., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00623 · Cited by 3
“Skinning is fundamental to 3D character animation, modeling surface deformations induced by skeletal motion [23, 25].”
Scanmove: Motion prediction and transfer for unregistered body meshes
Besnier, T., Arguillère, S., & Daoudi, M. (2025) · Computers & Graphics · doi:10.1016/j.cag.2025.104409 · Cited by 4
“Recent approaches are breaking free of the need for a consistent skinning mapping [37, 35] but heavily rely on a good rigging.”
iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos
Peng, W., Lv, J., Lu, C., & Savva, M. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00056 · Cited by 22
“In contrast, our method does not rely on object retrieval or fine-tuning, and is inherently more general and scalable.”
3D asset generation: a survey of evolution towards autoregressive and agent-driven paradigms
Fan, H., Chen, H., Huang, Z., Liu, Z., & Sheng, L. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-025-50381-5 · Cited by 1
Motion2VecSets: Non-Rigid Shape Reconstruction and Tracking With 4D Latent Set Diffusion
Tang, J., Cao, W., Zhang, B., Luo, C., Liu, Y., & Nießner, M. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3680779 · Cited by 4
“Similarly, methods such as RigAnything [96] and MagicArticu-late [97] enable explicit skeleton and skinning weight prediction from raw meshes.”
Metadata
- Authors
- Liu, I., Xu, Z., Yifan, W., Tan, H., Xu, Z., Wang, X., Su, H., & Shi, Z.
- Affiliations
- University of California San Diego (US)
- Adobe Systems (United States) (US)
- Adobe Research, San Jose, USA
- Venue
- ACM Transactions on Graphics
- Published
- 2025-07-27
- Volume
- 44
- Issue
- 4
- Pages
- 1-12
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W4412673671
- Cited by
- 12
- References
- 18
- Citations by year
- 2026: 10 · 2025: 2
- FWCI
- 5.22
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Transactions on Graphics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- 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
- autoregressive transformers, skinning weights, diffusion models
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 2026-10-29, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-29 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets. https://app.cochat.ai/papers/10.1145/3731149
- The paper
- Liu, I., Xu, Z., Yifan, W., Tan, H., Xu, Z., Wang, X., Su, H., & Shi, Z. (2025). RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets. ACM Transactions on Graphics. https://doi.org/10.1145/3731149
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.