FlashTex: Fast Relightable Mesh Texturing with LightControlNet
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929548034048000 |
|---|---|
| author | Deng, Kangle Omernick, Timothy Weiss, Alexander Ramanan, Deva Zhu, Jun-Yan Zhou, Tinghui Agrawala, Maneesh |
| author_facet | Deng, Kangle Omernick, Timothy Weiss, Alexander Ramanan, Deva Zhu, Jun-Yan Zhou, Tinghui Agrawala, Maneesh |
| contents | Manually creating textures for 3D meshes is time-consuming, even for expert visual content creators. We propose a fast approach for automatically texturing an input 3D mesh based on a user-provided text prompt. Importantly, our approach disentangles lighting from surface material/reflectance in the resulting texture so that the mesh can be properly relit and rendered in any lighting environment. We introduce LightControlNet, a new text-to-image model based on the ControlNet architecture, which allows the specification of the desired lighting as a conditioning image to the model. Our text-to-texture pipeline then constructs the texture in two stages. The first stage produces a sparse set of visually consistent reference views of the mesh using LightControlNet. The second stage applies a texture optimization based on Score Distillation Sampling (SDS) that works with LightControlNet to increase the texture quality while disentangling surface material from lighting. Our algorithm is significantly faster than previous text-to-texture methods, while producing high-quality and relightable textures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13251 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FlashTex: Fast Relightable Mesh Texturing with LightControlNet Deng, Kangle Omernick, Timothy Weiss, Alexander Ramanan, Deva Zhu, Jun-Yan Zhou, Tinghui Agrawala, Maneesh Graphics Computer Vision and Pattern Recognition Machine Learning Manually creating textures for 3D meshes is time-consuming, even for expert visual content creators. We propose a fast approach for automatically texturing an input 3D mesh based on a user-provided text prompt. Importantly, our approach disentangles lighting from surface material/reflectance in the resulting texture so that the mesh can be properly relit and rendered in any lighting environment. We introduce LightControlNet, a new text-to-image model based on the ControlNet architecture, which allows the specification of the desired lighting as a conditioning image to the model. Our text-to-texture pipeline then constructs the texture in two stages. The first stage produces a sparse set of visually consistent reference views of the mesh using LightControlNet. The second stage applies a texture optimization based on Score Distillation Sampling (SDS) that works with LightControlNet to increase the texture quality while disentangling surface material from lighting. Our algorithm is significantly faster than previous text-to-texture methods, while producing high-quality and relightable textures. |
| title | FlashTex: Fast Relightable Mesh Texturing with LightControlNet |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.13251 |