Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917620692811776 |
|---|---|
| author | Ye, Zhenhui Zhong, Tianyun Ren, Yi Yang, Jiaqi Li, Weichuang Huang, Jiawei Jiang, Ziyue He, Jinzheng Huang, Rongjie Liu, Jinglin Zhang, Chen Yin, Xiang Ma, Zejun Zhao, Zhou |
| author_facet | Ye, Zhenhui Zhong, Tianyun Ren, Yi Yang, Jiaqi Li, Weichuang Huang, Jiawei Jiang, Ziyue He, Jinzheng Huang, Rongjie Liu, Jinglin Zhang, Chen Yin, Xiang Ma, Zejun Zhao, Zhou |
| contents | One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talking face animation. Besides, while the existing works mainly focus on synthesizing the head part, it is also vital to generate natural torso and background segments to obtain a realistic talking portrait video. To address these limitations, we present Real3D-Potrait, a framework that (1) improves the one-shot 3D reconstruction power with a large image-to-plane model that distills 3D prior knowledge from a 3D face generative model; (2) facilitates accurate motion-conditioned animation with an efficient motion adapter; (3) synthesizes realistic video with natural torso movement and switchable background using a head-torso-background super-resolution model; and (4) supports one-shot audio-driven talking face generation with a generalizable audio-to-motion model. Extensive experiments show that Real3D-Portrait generalizes well to unseen identities and generates more realistic talking portrait videos compared to previous methods. Video samples and source code are available at https://real3dportrait.github.io . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_08503 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis Ye, Zhenhui Zhong, Tianyun Ren, Yi Yang, Jiaqi Li, Weichuang Huang, Jiawei Jiang, Ziyue He, Jinzheng Huang, Rongjie Liu, Jinglin Zhang, Chen Yin, Xiang Ma, Zejun Zhao, Zhou Computer Vision and Pattern Recognition One-shot 3D talking portrait generation aims to reconstruct a 3D avatar from an unseen image, and then animate it with a reference video or audio to generate a talking portrait video. The existing methods fail to simultaneously achieve the goals of accurate 3D avatar reconstruction and stable talking face animation. Besides, while the existing works mainly focus on synthesizing the head part, it is also vital to generate natural torso and background segments to obtain a realistic talking portrait video. To address these limitations, we present Real3D-Potrait, a framework that (1) improves the one-shot 3D reconstruction power with a large image-to-plane model that distills 3D prior knowledge from a 3D face generative model; (2) facilitates accurate motion-conditioned animation with an efficient motion adapter; (3) synthesizes realistic video with natural torso movement and switchable background using a head-torso-background super-resolution model; and (4) supports one-shot audio-driven talking face generation with a generalizable audio-to-motion model. Extensive experiments show that Real3D-Portrait generalizes well to unseen identities and generates more realistic talking portrait videos compared to previous methods. Video samples and source code are available at https://real3dportrait.github.io . |
| title | Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.08503 |