Animating the Uncaptured: Humanoid Mesh Animation with Video 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_ | 1866908276047740928 |
|---|---|
| author | Millán, Marc Benedí San Dai, Angela Nießner, Matthias |
| author_facet | Millán, Marc Benedí San Dai, Angela Nießner, Matthias |
| contents | Animation of humanoid characters is essential in various graphics applications, but requires significant time and cost to create realistic animations. We propose an approach to synthesize 4D animated sequences of input static 3D humanoid meshes, leveraging strong generalized motion priors from generative video models -- as such video models contain powerful motion information covering a wide variety of human motions. From an input static 3D humanoid mesh and a text prompt describing the desired animation, we synthesize a corresponding video conditioned on a rendered image of the 3D mesh. We then employ an underlying SMPL representation to animate the corresponding 3D mesh according to the video-generated motion, based on our motion optimization. This enables a cost-effective and accessible solution to enable the synthesis of diverse and realistic 4D animations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15996 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models Millán, Marc Benedí San Dai, Angela Nießner, Matthias Graphics Computer Vision and Pattern Recognition Animation of humanoid characters is essential in various graphics applications, but requires significant time and cost to create realistic animations. We propose an approach to synthesize 4D animated sequences of input static 3D humanoid meshes, leveraging strong generalized motion priors from generative video models -- as such video models contain powerful motion information covering a wide variety of human motions. From an input static 3D humanoid mesh and a text prompt describing the desired animation, we synthesize a corresponding video conditioned on a rendered image of the 3D mesh. We then employ an underlying SMPL representation to animate the corresponding 3D mesh according to the video-generated motion, based on our motion optimization. This enables a cost-effective and accessible solution to enable the synthesis of diverse and realistic 4D animations. |
| title | Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.15996 |