T2Bs: Text-to-Character Blendshapes via Video Generation
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_ | 1866916972768264192 |
|---|---|
| author | Luo, Jiahao Wang, Chaoyang Vasilkovsky, Michael Shakhrai, Vladislav Liu, Di Zhuang, Peiye Tulyakov, Sergey Wonka, Peter Lee, Hsin-Ying Davis, James Wang, Jian |
| author_facet | Luo, Jiahao Wang, Chaoyang Vasilkovsky, Michael Shakhrai, Vladislav Liu, Di Zhuang, Peiye Tulyakov, Sergey Wonka, Peter Lee, Hsin-Ying Davis, James Wang, Jian |
| contents | We present T2Bs, a framework for generating high-quality, animatable character head morphable models from text by combining static text-to-3D generation with video diffusion. Text-to-3D models produce detailed static geometry but lack motion synthesis, while video diffusion models generate motion with temporal and multi-view geometric inconsistencies. T2Bs bridges this gap by leveraging deformable 3D Gaussian splatting to align static 3D assets with video outputs. By constraining motion with static geometry and employing a view-dependent deformation MLP, T2Bs (i) outperforms existing 4D generation methods in accuracy and expressiveness while reducing video artifacts and view inconsistencies, and (ii) reconstructs smooth, coherent, fully registered 3D geometries designed to scale for building morphable models with diverse, realistic facial motions. This enables synthesizing expressive, animatable character heads that surpass current 4D generation techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_10678 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | T2Bs: Text-to-Character Blendshapes via Video Generation Luo, Jiahao Wang, Chaoyang Vasilkovsky, Michael Shakhrai, Vladislav Liu, Di Zhuang, Peiye Tulyakov, Sergey Wonka, Peter Lee, Hsin-Ying Davis, James Wang, Jian Graphics We present T2Bs, a framework for generating high-quality, animatable character head morphable models from text by combining static text-to-3D generation with video diffusion. Text-to-3D models produce detailed static geometry but lack motion synthesis, while video diffusion models generate motion with temporal and multi-view geometric inconsistencies. T2Bs bridges this gap by leveraging deformable 3D Gaussian splatting to align static 3D assets with video outputs. By constraining motion with static geometry and employing a view-dependent deformation MLP, T2Bs (i) outperforms existing 4D generation methods in accuracy and expressiveness while reducing video artifacts and view inconsistencies, and (ii) reconstructs smooth, coherent, fully registered 3D geometries designed to scale for building morphable models with diverse, realistic facial motions. This enables synthesizing expressive, animatable character heads that surpass current 4D generation techniques. |
| title | T2Bs: Text-to-Character Blendshapes via Video Generation |
| topic | Graphics |
| url | https://arxiv.org/abs/2509.10678 |