TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation
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_ | 1866914720240369664 |
|---|---|
| author | Liu, Yufei Zhu, Junwei Tang, Junshu Zhang, Shijie Zhang, Jiangning Cao, Weijian Wang, Chengjie Wu, Yunsheng Huang, Dongjin |
| author_facet | Liu, Yufei Zhu, Junwei Tang, Junshu Zhang, Shijie Zhang, Jiangning Cao, Weijian Wang, Chengjie Wu, Yunsheng Huang, Dongjin |
| contents | Texturing 3D humans with semantic UV maps remains a challenge due to the difficulty of acquiring reasonably unfolded UV. Despite recent text-to-3D advancements in supervising multi-view renderings using large text-to-image (T2I) models, issues persist with generation speed, text consistency, and texture quality, resulting in data scarcity among existing datasets. We present TexDreamer, the first zero-shot multimodal high-fidelity 3D human texture generation model. Utilizing an efficient texture adaptation finetuning strategy, we adapt large T2I model to a semantic UV structure while preserving its original generalization capability. Leveraging a novel feature translator module, the trained model is capable of generating high-fidelity 3D human textures from either text or image within seconds. Furthermore, we introduce ArTicuLated humAn textureS (ATLAS), the largest high-resolution (1024 X 1024) 3D human texture dataset which contains 50k high-fidelity textures with text descriptions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12906 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation Liu, Yufei Zhu, Junwei Tang, Junshu Zhang, Shijie Zhang, Jiangning Cao, Weijian Wang, Chengjie Wu, Yunsheng Huang, Dongjin Computer Vision and Pattern Recognition Texturing 3D humans with semantic UV maps remains a challenge due to the difficulty of acquiring reasonably unfolded UV. Despite recent text-to-3D advancements in supervising multi-view renderings using large text-to-image (T2I) models, issues persist with generation speed, text consistency, and texture quality, resulting in data scarcity among existing datasets. We present TexDreamer, the first zero-shot multimodal high-fidelity 3D human texture generation model. Utilizing an efficient texture adaptation finetuning strategy, we adapt large T2I model to a semantic UV structure while preserving its original generalization capability. Leveraging a novel feature translator module, the trained model is capable of generating high-fidelity 3D human textures from either text or image within seconds. Furthermore, we introduce ArTicuLated humAn textureS (ATLAS), the largest high-resolution (1024 X 1024) 3D human texture dataset which contains 50k high-fidelity textures with text descriptions. |
| title | TexDreamer: Towards Zero-Shot High-Fidelity 3D Human Texture Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2403.12906 |