Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913539377070080 |
|---|---|
| author | Vainer, Shimon Kutsy, Konstantin De Nigris, Dante Rowles, Ciara Elizarov, Slava Donné, Simon |
| author_facet | Vainer, Shimon Kutsy, Konstantin De Nigris, Dante Rowles, Ciara Elizarov, Slava Donné, Simon |
| contents | Multi-view consistency remains a challenge for image diffusion models. Even within the Text-to-Texture problem, where perfect geometric correspondences are known a priori, many methods fail to yield aligned predictions across views, necessitating non-trivial fusion methods to incorporate the results onto the original mesh. We explore this issue for a Collaborative Control workflow specifically in PBR Text-to-Texture. Collaborative Control directly models PBR image probability distributions, including normal bump maps; to our knowledge, the only diffusion model to directly output full PBR stacks. We discuss the design decisions involved in making this model multi-view consistent, and demonstrate the effectiveness of our approach in ablation studies, as well as practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_06985 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control Vainer, Shimon Kutsy, Konstantin De Nigris, Dante Rowles, Ciara Elizarov, Slava Donné, Simon Computer Vision and Pattern Recognition Graphics Multi-view consistency remains a challenge for image diffusion models. Even within the Text-to-Texture problem, where perfect geometric correspondences are known a priori, many methods fail to yield aligned predictions across views, necessitating non-trivial fusion methods to incorporate the results onto the original mesh. We explore this issue for a Collaborative Control workflow specifically in PBR Text-to-Texture. Collaborative Control directly models PBR image probability distributions, including normal bump maps; to our knowledge, the only diffusion model to directly output full PBR stacks. We discuss the design decisions involved in making this model multi-view consistent, and demonstrate the effectiveness of our approach in ablation studies, as well as practical applications. |
| title | Jointly Generating Multi-view Consistent PBR Textures using Collaborative Control |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2410.06985 |