Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909142882451456 |
|---|---|
| author | Gong, Chaoqun Dai, Yuqin Li, Ronghui Bao, Achun Li, Jun Yang, Jian Zhang, Yachao Li, Xiu |
| author_facet | Gong, Chaoqun Dai, Yuqin Li, Ronghui Bao, Achun Li, Jun Yang, Jian Zhang, Yachao Li, Xiu |
| contents | Generating 3D human models directly from text helps reduce the cost and time of character modeling. However, achieving multi-attribute controllable and realistic 3D human avatar generation is still challenging due to feature coupling and the scarcity of realistic 3D human avatar datasets. To address these issues, we propose Text2Avatar, which can generate realistic-style 3D avatars based on the coupled text prompts. Text2Avatar leverages a discrete codebook as an intermediate feature to establish a connection between text and avatars, enabling the disentanglement of features. Furthermore, to alleviate the scarcity of realistic style 3D human avatar data, we utilize a pre-trained unconditional 3D human avatar generation model to obtain a large amount of 3D avatar pseudo data, which allows Text2Avatar to achieve realistic style generation. Experimental results demonstrate that our method can generate realistic 3D avatars from coupled textual data, which is challenging for other existing methods in this field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_00711 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute Gong, Chaoqun Dai, Yuqin Li, Ronghui Bao, Achun Li, Jun Yang, Jian Zhang, Yachao Li, Xiu Computer Vision and Pattern Recognition Artificial Intelligence Generating 3D human models directly from text helps reduce the cost and time of character modeling. However, achieving multi-attribute controllable and realistic 3D human avatar generation is still challenging due to feature coupling and the scarcity of realistic 3D human avatar datasets. To address these issues, we propose Text2Avatar, which can generate realistic-style 3D avatars based on the coupled text prompts. Text2Avatar leverages a discrete codebook as an intermediate feature to establish a connection between text and avatars, enabling the disentanglement of features. Furthermore, to alleviate the scarcity of realistic style 3D human avatar data, we utilize a pre-trained unconditional 3D human avatar generation model to obtain a large amount of 3D avatar pseudo data, which allows Text2Avatar to achieve realistic style generation. Experimental results demonstrate that our method can generate realistic 3D avatars from coupled textual data, which is challenging for other existing methods in this field. |
| title | Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2401.00711 |