MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915211510808576 |
|---|---|
| author | Zhu, Lingting Ye, Jingrui Zhang, Runze Hu, Zeyu Yin, Yingda Li, Lanjiong Chen, Jinnan Qian, Shengju Wang, Xin Liao, Qingmin Yu, Lequan |
| author_facet | Zhu, Lingting Ye, Jingrui Zhang, Runze Hu, Zeyu Yin, Yingda Li, Lanjiong Chen, Jinnan Qian, Shengju Wang, Xin Liao, Qingmin Yu, Lequan |
| contents | Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials. In this work, we propose MuMA, a method for 3D PBR texturing through Multi-channel Multi-view generation and Agentic post-processing. Our approach features two key innovations: 1) We opt to model shaded and albedo appearance channels, where the shaded channels enables the integration intrinsic decomposition modules for material properties. 2) Leveraging multimodal large language models, we emulate artists' techniques for material assessment and selection. Experiments demonstrate that MuMA achieves superior results in visual quality and material fidelity compared to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_18461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing Zhu, Lingting Ye, Jingrui Zhang, Runze Hu, Zeyu Yin, Yingda Li, Lanjiong Chen, Jinnan Qian, Shengju Wang, Xin Liao, Qingmin Yu, Lequan Computer Vision and Pattern Recognition Current methods for 3D generation still fall short in physically based rendering (PBR) texturing, primarily due to limited data and challenges in modeling multi-channel materials. In this work, we propose MuMA, a method for 3D PBR texturing through Multi-channel Multi-view generation and Agentic post-processing. Our approach features two key innovations: 1) We opt to model shaded and albedo appearance channels, where the shaded channels enables the integration intrinsic decomposition modules for material properties. 2) Leveraging multimodal large language models, we emulate artists' techniques for material assessment and selection. Experiments demonstrate that MuMA achieves superior results in visual quality and material fidelity compared to existing methods. |
| title | MuMA: 3D PBR Texturing via Multi-Channel Multi-View Generation and Agentic Post-Processing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.18461 |