AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908419829530624 |
|---|---|
| author | Huang, Zehuan Feng, Haoran Sun, Yangtian Guo, Yuanchen Cao, Yanpei Sheng, Lu |
| author_facet | Huang, Zehuan Feng, Haoran Sun, Yangtian Guo, Yuanchen Cao, Yanpei Sheng, Lu |
| contents | We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method represents 3D motion as multi-view, multi-frame 2D pose maps, and enables joint video-pose diffusion conditioned on template renderings and a textual motion prompt. We introduce shared positional encodings and modality-aware embeddings to ensure spatial-temporal alignment between video and pose sequences, effectively transferring video priors to motion generation task. The resulting multi-view pose sequences are triangulated into 3D joint positions and converted into mesh animation via inverse kinematics. Trained on a newly curated dataset of 160,000 rigged sequences, AnimaX achieves state-of-the-art results on VBench in generalization, motion fidelity, and efficiency, offering a scalable solution for category-agnostic 3D animation. Project page: \href{https://anima-x.github.io/}{https://anima-x.github.io/}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19851 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models Huang, Zehuan Feng, Haoran Sun, Yangtian Guo, Yuanchen Cao, Yanpei Sheng, Lu Computer Vision and Pattern Recognition We present AnimaX, a feed-forward 3D animation framework that bridges the motion priors of video diffusion models with the controllable structure of skeleton-based animation. Traditional motion synthesis methods are either restricted to fixed skeletal topologies or require costly optimization in high-dimensional deformation spaces. In contrast, AnimaX effectively transfers video-based motion knowledge to the 3D domain, supporting diverse articulated meshes with arbitrary skeletons. Our method represents 3D motion as multi-view, multi-frame 2D pose maps, and enables joint video-pose diffusion conditioned on template renderings and a textual motion prompt. We introduce shared positional encodings and modality-aware embeddings to ensure spatial-temporal alignment between video and pose sequences, effectively transferring video priors to motion generation task. The resulting multi-view pose sequences are triangulated into 3D joint positions and converted into mesh animation via inverse kinematics. Trained on a newly curated dataset of 160,000 rigged sequences, AnimaX achieves state-of-the-art results on VBench in generalization, motion fidelity, and efficiency, offering a scalable solution for category-agnostic 3D animation. Project page: \href{https://anima-x.github.io/}{https://anima-x.github.io/}. |
| title | AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.19851 |