AniGen: Unified S 3 Fields for Animatable 3D Asset Generation
Open accessAbstract
Animatable 3D assets, defined as geometry equipped with an articulated skeleton and skinning weights, are fundamental to interactive graphics, embodied agents, and animation production. While recent 3D generative models can synthesize visually plausible shapes from images, the results are typically static. Obtaining usable rigs via post-hoc auto-rigging is brittle and often produces skeletons that are topologically inconsistent with the generated geometry. We present AniGen , a unified framework that directly generates animate-ready 3D assets conditioned on a single image. Our key insight is to represent shape, skeleton, and skinning as mutually consistent S 3 Fields (Shape, Skeleton, Skin) defined over a shared spatial domain. To enable the robust learning of these fields, we introduce two technical innovations: (i) a confidence-decaying skeleton field that explicitly handles the geometric ambiguity of bone prediction at Voronoi boundaries, and (ii) a dual skin feature field that decouples skinning weights from specific joint counts, allowing a fixed-architecture network to predict rigs of arbitrary complexity. Built upon a two-stage flow-matching pipeline, AniGen first synthesizes a sparse structural scaffold and then generates dense geometry and articulation in a structured latent space. Extensive experiments demonstrate that AniGen substantially outperforms state-of-the-art sequential baselines in rig validity and animation quality, generalizing effectively to in-the-wild…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
AniGen produces a discrete skeleton through a post-processing clustering step.
“They produce a discrete skeleton through a post-processing clustering step.”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Huang et al. [2026]
AniGen is concurrent work that directly generates animatable 3D assets by representing shape, skeleton, and skinning as continuous S3 fields over a shared spatial domain.
“AniGen Huang et al. [2026] is concurrent work that directly generates animatable 3D assets by representing shape, skeleton, and skinning as continuous S 3 fields over a shared spatial domain.”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Huang et al. [2026]
Since the generated meshes do not share vertex correspondence with the reference mesh, we follow Anigen and align predicted skinning weights to the reference skeleton using optimal transport induced by the Wasserstein distance between predicted and reference joints.
“Since the generated meshes do not share vertex correspondence with the reference mesh, we follow Anigen Huang et al. [2026] and align predicted skinning weights to the reference skeleton using optimal transport induced by the Wasserstein distance between predicted and reference joints.”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Huang et al. [2026]
On ArticulationXL, Rigel3D substantially improves all skeleton metrics over AniGen, reducing J2J from 10.667 to 7.168 (32.8% relative reduction), J2B from 9.715 to 6.036 (37.9%), and B2B from 8.601 to 5.976 (30.5%).
“On ArticulationXL, Rigel3D substantially improves all skeleton metrics over AniGen, reducing J2J from 10 . 667 to 7 . 168 ( 32 . 8% relative reduction), J2B from 9 . 715 to 6 . 036 ( 37 . 9% ), and B2B from 8 . 601 to 5 . 976 ( 30 . 5% ).”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Huang et al. [2026]
Our ArticulationXL numbers differ from those reported by AniGen because, at the time of submission, their test images, rendering parameters, and evaluation code were not publicly available.
“We note that our ArticulationXL numbers differ from those reported by AniGen because, at the time of submission, their test images, rendering parameters, and evaluation code were not publicly available.”
From Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation (2026) · cites this paper as Huang et al. [2026]
Cites
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534 · see citing works
Self-citationNeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852 · see citing works
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Kerbl, B., Kopanas, G., Leimkuehler, T., & Drettakis, G. (2023) · ACM Transactions on Graphics · doi:10.1145/3592433 · Cited by 6,025 · see citing works
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 · see citing works
Zero-1-to-3: Zero-shot One Image to 3D Object
Liu, R., Wu, R., Hoorick, B. V., Tokmakov, P., Zakharov, S., & Vondrick, C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00853 · Cited by 888 · see citing works
Objaverse: A Universe of Annotated 3D Objects
Deitke, M., Schwenk, D., Salvador, J., Weihs, L., Michel, O., VanderBilt, E., Schmidt, L., Ehsanit, K., Kembhavi, A., & Farhadi, A. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01263 · Cited by 725 · see citing works
A class of Wasserstein metrics for probability distributions.
Givens, C. R., & Shortt, R. M. (1984) · The Michigan Mathematical Journal · doi:10.1307/mmj/1029003026 · Cited by 590 · see citing works
Wonder3D: Single Image to 3D Using Cross-Domain Diffusion
Long, X., Guo, Y., Lin, C. C., Liu, Y., Dou, Z., Liu, L., Ma, Y., Zhang, S.-H., Habermann, M., Theobalt, C., et al. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00951 · Cited by 397 · see citing works
Self-citationZero-Shot Text-Guided Object Generation with Dream Fields
Jain, A., Mildenhall, B., Barron, J. T., Abbeel, P., & Poole, B. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00094 · Cited by 395 · see citing works
Structured 3D Latents for Scalable and Versatile 3D Generation
Xiang, J., Lv, Z., Xu, S., Yu, D., Wang, R., Zhang, B., Chen, D., Tong, X., & Yang, J. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02000 · Cited by 318 · see citing works
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
Huang, Y., Sun, Y.-T., Yang, Z., Lyu, X., Cao, Y., & Qi, X. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00404 · Cited by 202 · see citing works
Self-citationCLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets
Zhang, L., Wang, Z., Zhang, Q., Qiu, Q., Pang, A., Jiang, H., Yang, W., Xu, L., & Jingyi Yu, A. (2024) · ACM Transactions on Graphics · doi:10.1145/3658146 · Cited by 173 · see citing works
Zou, Z., Yu, Z., Guo, Y., Li, Y., Ding, L., Cao, Y., & Zhang, S. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.00983 · Cited by 155 · see citing works
Self-citationObjaverse-XL: A Universe of 10M+ 3D Objects
Deitke, M., Liu, R., Wallingford, M., Ngo, H., Michel, O., Kusupati, A., Fan, A., Laforte, C., Voleti, V., Gadre, S. Y., et al. (2023) · neural information processing systems · doi:10.52202/075280-1554 · Cited by 148 · see citing works
Xu, Z., Zhou, Y., Kalogerakis, E., Landreth, C., & Singh, K. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392379 · Cited by 126 · cited 1× · see citing works
“RigNet [Xu et al. 2020] further advanced rigging through deep learning but was limited to templates and T-poses.”
ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
Zhang, Y., Dong, W., Tang, F., Huang, N., Huang, H., Ma, C., Lee, T., Deußen, O., & Xu, C. (2023) · ACM Transactions on Graphics · doi:10.1145/3618342 · Cited by 111 · see citing works
Flexible Isosurface Extraction for Gradient-Based Mesh Optimization
Shen, T., Munkberg, J., Hasselgren, J., Yin, K., Wang, Z., Chen, W., Gojčič, Ž., Fidler, S., Sharp, N., & Gao, J. (2023) · ACM Transactions on Graphics · doi:10.1145/3592430 · Cited by 102 · see citing works
Learning skeletal articulations with neural blend shapes
Li, P., Aberman, K., Hanocka, R., Liu, L., Sorkine‐Hornung, O., & Chen, B. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459852 · Cited by 101 · see citing works
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
Gao, R., Hołyński, A., Henzler, P., Brussee, A., Martin-Brualla, R., Srinivasan, P. P., Barron, J. T., & Poole, B. (2024) · neural information processing systems · doi:10.52202/079017-2403 · Cited by 62 · see citing works
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Wu, S., Lin, Y., Zhang, F., Zeng, Y., Xu, J., Torr, P. H. S., Cao, X., & Yao, Y. (2024) · neural information processing systems · doi:10.52202/079017-3873 · Cited by 57 · see citing works
RigMesh: automatic rigging for part-based shape modeling and deformation
Borosán, P., Jin, M., DeCarlo, D., Gingold, Y., & Nealen, A. (2012) · ACM Transactions on Graphics · doi:10.1145/2366145.2366217 · Cited by 53 · cited 1× · see citing works
“Automatic rigging [Bærentzen et al. 2014; Borosán et al. 2012; Pandey et al. 2022; Xu et al. 2019] aims to equip static 3D meshes with skeletons and skinning weights to enable animation.”
Predicting Animation Skeletons for 3D Articulated Models via Volumetric Nets
Xu, Z., Zhou, Y., Kalogerakis, E., & Singh, K. S. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00041 · Cited by 52 · see citing works
CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
Wu, R., Gao, R., Poole, B., Trevithick, A., Zheng, C., Barron, J. T., & Hołyński, A. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02427 · Cited by 48 · see citing works
liu, H.-T. D., & Jacobson, A. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356495 · Cited by 36 · see citing works
Interactive shape modeling using a skeleton-mesh co-representation
Bærentzen, J. A., Abdrashitov, R., & Singh, K. S. (2014) · ACM Transactions on Graphics · doi:10.1145/2601097.2601226 · Cited by 34 · see citing works
SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
He, X., Zou, Z., Chen, C.-H., Guo, Y.-C., Ding, L., Yuan, C., Ouyang, W., Cao, Y., & Li, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01375 · Cited by 26 · see citing works
Self-citationDora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
Chen, R., Zhang, J., Liang, Y., Luo, G., Li, W., Liu, J., Li, X., Long, X., Feng, J., & Tan, P. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01515 · Cited by 24 · see citing works
TARig: Adaptive template-aware neural rigging for humanoid characters
Ma, J., & Zhang, D. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.05.018 · Cited by 18 · see citing works
TARig: Adaptive template-aware neural rigging for humanoid characters
Ma, J., & Zhang, D. (2023) · doi:10.2139/ssrn.4326447 · Cited by 17 · cited 1×
“Subsequent works, such as Neural Blend Shapes [Li et al. 2021] and TARig [Ma and Zhang 2023], tackled rigging and skinning for humanoid characters, while MoRig [Xu et al. 2022] used deforming point clouds for guidance.”
Morig: Motion-Aware Rigging of Character Meshes from Point Clouds
Xu, Z., Zhou, Y., Yi, L., & Kalogerakis, E. (2022) · SIGGRAPH Asia Conference Papers · doi:10.1145/3550469.3555390 · Cited by 16 · see citing works
AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
Wu, Z., Yu, C., Wang, F., & Bai, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01259 · Cited by 14 · see citing works
RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
Liu, I., Xu, Z., Yifan, W., Tan, H., Xu, Z., Wang, X., Su, H., & Shi, Z. (2025) · ACM Transactions on Graphics · doi:10.1145/3731149 · Cited by 12 · cited 4× · see citing works
“…strategy to bridge this gap is a sequential “generate-then-rig” pipeline: first synthesize a static mesh using a state-of-the-art 3D generator [Xiang et al. 2025b], followed by an off-the-shelf auto-rigging algorithm [Deng et al. 2025; Liu et al. 2025; Song et al. 2025a; Zhang et al. 2025].”
InfluentialOne Model to Rig Them All: Diverse Skeleton Rigging with UniRig
Zhang, J.-P., Pu, C.-F., Guo, M.-H., Cao, Y.-P., & Hu, S.-M. (2025) · ACM Transactions on Graphics · doi:10.1145/3730930 · Cited by 12 · cited 3× · see citing works
“…strategy to bridge this gap is a sequential “generate-then-rig” pipeline: first synthesize a static mesh using a state-of-the-art 3D generator [Xiang et al. 2025b], followed by an off-the-shelf auto-rigging algorithm [Deng et al. 2025; Liu et al. 2025; Song et al. 2025a; Zhang et al. 2025].”
Self-citationDRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Sun, M., Chen, J., Dong, J., Chen, Y., Jiang, X., Mao, S., Jiang, P., Wang, J., Dai, B., & Huang, R. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01972 · Cited by 12 · see citing works
MagicArticulate: Make Your 3D Models Articulation-Ready
Song, C., Zhang, J., Xiu, L., Yang, F., Chen, Y., Xu, Z., Liew, J. H., Guo, X., Liu, F., Feng, J., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01491 · Cited by 12 · see citing works
AnyTop: Character Animation Diffusion with Any Topology
Gat, I., Raab, S., Tevet, G., Reshef, Y., Bermano, A. H., & Cohen-Or, D. (2025) · Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers · doi:10.1145/3721238.3730621 · Cited by 9 · see citing works
Skinned Motion Retargeting With Preservation of Body Part Relationships
Zhang, J.-Q., Wang, M., Zhang, F., & Zhang, F. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3423426 · Cited by 6 · see citing works
Anymate: A Dataset and Baselines for Learning 3D Object Rigging
Deng, Y., Zhang, Y., Geng, C., Wu, S., & Wu, J. (2025) · Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers · doi:10.1145/3721238.3730743 · Cited by 6 · see citing works
Pandey, K., Bærentzen, J. A., & Singh, K. S. (2022) · doi:10.1145/3528233.3530754 · Cited by 4 · see citing works
ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
Chen, H., Lan, Y., Chen, Y., & Pan, X. (2025) · Proceedings of the SIGGRAPH Asia 2025 Conference Papers · doi:10.1145/3757377.3763922 · Cited by 4 · see citing works
AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
Huang, Z., Feng, H., Sun, Y.-T., Guo, Y.-C., Cao, Y.-P., & Sheng, L. (2025) · Proceedings of the SIGGRAPH Asia 2025 Conference Papers · doi:10.1145/3757377.3763885 · Cited by 3 · see citing works
Self-citationS$^{2}$VG: 3D Stereoscopic and Spatial Video Generation via Denoising Frame Matrix
Dai, P., Tan, F., Xu, Q., Huang, Y., Futschik, D., Du, R., Fanello, S., Zhang, Y., & Qi, X. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3692948 · Cited by 2 · see citing works
Self-citationSS4D: Native 4D Generative Model via Structured Spacetime Latents
Li, Z., Zhang, M., Wu, T., Tan, J., Wang, J., & Lin, D. (2025) · ACM Transactions on Graphics · doi:10.1145/3763302 · Cited by 1 · see citing works
Rigidity-Aware 3D Gaussian Deformation from a Single Image
Kim, J., Bang, J., Seo, S., & Joo, K. (2025) · SIGGRAPH Asia Conference Papers · doi:10.1145/3757377.3763937 · Cited by 1 · see citing works
SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix
Dai, P., Tan, F., Xu, Q., Futschik, D., Du, R., Fanello, S., Qi, X., & Zhang, Y. (2024) · arXiv · doi:10.48550/arxiv.2407.00367 · cited 1×
“Cat4D [Wu et al. 2025a] and SVG [Dai et al. 2025] use diffusion models to generate spatial-temporal frame matrices for dynamic scenes but are limited in view range.”
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Rigel3D: Rig-aware Latents for Animation-Ready 3D Asset Generation
Chatzis, N., Loizou, M., & Kalogerakis, E. (2026) · arXiv · doi:10.48550/arxiv.2605.13129
- Authors
- Huang, Y.-H., Zou, Z.-X., He, Y., Chang, C., Pu, C.-F., Yang, Z., Guo, Y.-C., Cao, Y.-P., & Qi, X.
- Affiliations
- University of Hong Kong (HK)
- VAST, Beijing, China
- Chinese University of Hong Kong (HK)
- Tsinghua University, Beijing, China
- VAST, Shanghai, China
- ORCID
- Venue
- ACM Transactions on Graphics
- Published
- 2026-07-03
- Volume
- 45
- Issue
- 4
- Pages
- 1-16
- ISSN
- 0730-0301 (ISSN-L)
- 1557-7368
- OpenAlex
- W7167253557
- Cited by
- 0
- References
- 43
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- ACM Transactions on Graphics (publishedVersion, cc-by)
- Funders
- Hong Kong Research Grant Council (17202422, 17212923, 17215025)
- International (Hong Kong, Macao, and Taiwan) Collaborative R&D Project, Beijing Major Science and Technology Project (Z251100007125016)
- Topics
- Physical Sciences › Engineering › Computational Mechanics › 3D Shape Modeling and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Keywords
- skinning weights, flow matching, 3D shape synthesis
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.
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
