DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913586232688640 |
|---|---|
| author | Sun, Mingze Chen, Junhao Dong, Junting Chen, Yurun Jiang, Xinyu Mao, Shiwei Jiang, Puhua Wang, Jingbo Dai, Bo Huang, Ruqi |
| author_facet | Sun, Mingze Chen, Junhao Dong, Junting Chen, Yurun Jiang, Xinyu Mao, Shiwei Jiang, Puhua Wang, Jingbo Dai, Bo Huang, Ruqi |
| contents | Recent advances in generative models have enabled high-quality 3D character reconstruction from multi-modal. However, animating these generated characters remains a challenging task, especially for complex elements like garments and hair, due to the lack of large-scale datasets and effective rigging methods. To address this gap, we curate AnimeRig, a large-scale dataset with detailed skeleton and skinning annotations. Building upon this, we propose DRiVE, a novel framework for generating and rigging 3D human characters with intricate structures. Unlike existing methods, DRiVE utilizes a 3D Gaussian representation, facilitating efficient animation and high-quality rendering. We further introduce GSDiff, a 3D Gaussian-based diffusion module that predicts joint positions as spatial distributions, overcoming the limitations of regression-based approaches. Extensive experiments demonstrate that DRiVE achieves precise rigging results, enabling realistic dynamics for clothing and hair, and surpassing previous methods in both quality and versatility. The code and dataset will be made public for academic use upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17423 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters Sun, Mingze Chen, Junhao Dong, Junting Chen, Yurun Jiang, Xinyu Mao, Shiwei Jiang, Puhua Wang, Jingbo Dai, Bo Huang, Ruqi Computer Vision and Pattern Recognition Recent advances in generative models have enabled high-quality 3D character reconstruction from multi-modal. However, animating these generated characters remains a challenging task, especially for complex elements like garments and hair, due to the lack of large-scale datasets and effective rigging methods. To address this gap, we curate AnimeRig, a large-scale dataset with detailed skeleton and skinning annotations. Building upon this, we propose DRiVE, a novel framework for generating and rigging 3D human characters with intricate structures. Unlike existing methods, DRiVE utilizes a 3D Gaussian representation, facilitating efficient animation and high-quality rendering. We further introduce GSDiff, a 3D Gaussian-based diffusion module that predicts joint positions as spatial distributions, overcoming the limitations of regression-based approaches. Extensive experiments demonstrate that DRiVE achieves precise rigging results, enabling realistic dynamics for clothing and hair, and surpassing previous methods in both quality and versatility. The code and dataset will be made public for academic use upon acceptance. |
| title | DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.17423 |