GUAVA: Generalizable Upper Body 3D Gaussian Avatar
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913969757749248 |
|---|---|
| author | Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Li, Yang Qin, Minghan Li, Yu Wang, Haoqian |
| author_facet | Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Li, Yang Qin, Minghan Li, Yu Wang, Haoqian |
| contents | Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03351 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GUAVA: Generalizable Upper Body 3D Gaussian Avatar Zhang, Dongbin Liu, Yunfei Lin, Lijian Zhu, Ye Li, Yang Qin, Minghan Li, Yu Wang, Haoqian Computer Vision and Pattern Recognition Reconstructing a high-quality, animatable 3D human avatar with expressive facial and hand motions from a single image has gained significant attention due to its broad application potential. 3D human avatar reconstruction typically requires multi-view or monocular videos and training on individual IDs, which is both complex and time-consuming. Furthermore, limited by SMPLX's expressiveness, these methods often focus on body motion but struggle with facial expressions. To address these challenges, we first introduce an expressive human model (EHM) to enhance facial expression capabilities and develop an accurate tracking method. Based on this template model, we propose GUAVA, the first framework for fast animatable upper-body 3D Gaussian avatar reconstruction. We leverage inverse texture mapping and projection sampling techniques to infer Ubody (upper-body) Gaussians from a single image. The rendered images are refined through a neural refiner. Experimental results demonstrate that GUAVA significantly outperforms previous methods in rendering quality and offers significant speed improvements, with reconstruction times in the sub-second range (0.1s), and supports real-time animation and rendering. |
| title | GUAVA: Generalizable Upper Body 3D Gaussian Avatar |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.03351 |