AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation
2026-04-09 • Graphics
GraphicsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors created AniGen, a method that makes 3D models ready for animation directly from a single image. Instead of making static shapes and then trying to add moving parts later, their system builds shape, skeleton, and skinning together so they fit well. They introduced new techniques to handle tricky parts like bone placement and different rig sizes. Tests show their method works better on various subjects like animals and machines compared to older approaches.
3D animationarticulated skeletonskinning weightsauto-riggingS3 FieldsVoronoi boundariesflow-matchinglatent space3D generative models
Authors
Yi-Hua Huang, Zi-Xin Zou, Yuting He, Chirui Chang, Cheng-Feng Pu, Ziyi Yang, Yuan-Chen Guo, Yan-Pei Cao, Xiaojuan Qi
Abstract
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 images across diverse categories including animals, humanoids, and machinery. Homepage: https://yihua7.github.io/AniGen-web/