AvatarArtist: Open-Domain 4D Avatarization
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_ | 1866916662732652544 |
|---|---|
| author | Liu, Hongyu Wang, Xuan Wan, Ziyu Ma, Yue Chen, Jingye Fan, Yanbo Shen, Yujun Song, Yibing Chen, Qifeng |
| author_facet | Liu, Hongyu Wang, Xuan Wan, Ziyu Ma, Yue Chen, Jingye Fan, Yanbo Shen, Yujun Song, Yibing Chen, Qifeng |
| contents | This work focuses on open-domain 4D avatarization, with the purpose of creating a 4D avatar from a portrait image in an arbitrary style. We select parametric triplanes as the intermediate 4D representation and propose a practical training paradigm that takes advantage of both generative adversarial networks (GANs) and diffusion models. Our design stems from the observation that 4D GANs excel at bridging images and triplanes without supervision yet usually face challenges in handling diverse data distributions. A robust 2D diffusion prior emerges as the solution, assisting the GAN in transferring its expertise across various domains. The synergy between these experts permits the construction of a multi-domain image-triplane dataset, which drives the development of a general 4D avatar creator. Extensive experiments suggest that our model, AvatarArtist, is capable of producing high-quality 4D avatars with strong robustness to various source image domains. The code, the data, and the models will be made publicly available to facilitate future studies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_19906 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AvatarArtist: Open-Domain 4D Avatarization Liu, Hongyu Wang, Xuan Wan, Ziyu Ma, Yue Chen, Jingye Fan, Yanbo Shen, Yujun Song, Yibing Chen, Qifeng Computer Vision and Pattern Recognition This work focuses on open-domain 4D avatarization, with the purpose of creating a 4D avatar from a portrait image in an arbitrary style. We select parametric triplanes as the intermediate 4D representation and propose a practical training paradigm that takes advantage of both generative adversarial networks (GANs) and diffusion models. Our design stems from the observation that 4D GANs excel at bridging images and triplanes without supervision yet usually face challenges in handling diverse data distributions. A robust 2D diffusion prior emerges as the solution, assisting the GAN in transferring its expertise across various domains. The synergy between these experts permits the construction of a multi-domain image-triplane dataset, which drives the development of a general 4D avatar creator. Extensive experiments suggest that our model, AvatarArtist, is capable of producing high-quality 4D avatars with strong robustness to various source image domains. The code, the data, and the models will be made publicly available to facilitate future studies. |
| title | AvatarArtist: Open-Domain 4D Avatarization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.19906 |