Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.16778 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913765067325440 |
|---|---|
| author | Huang, Zhipeng Yu, Wangbo Cheng, Xinhua Zhao, ChengShu Ge, Yunyang Guo, Mingyi Yuan, Li Tian, Yonghong |
| author_facet | Huang, Zhipeng Yu, Wangbo Cheng, Xinhua Zhao, ChengShu Ge, Yunyang Guo, Mingyi Yuan, Li Tian, Yonghong |
| contents | Indoor scene texture synthesis has garnered significant interest due to its important potential applications in virtual reality, digital media and creative arts. Existing diffusion-model-based researches either rely on per-view inpainting techniques, which are plagued by severe cross-view inconsistencies and conspicuous seams, or adopt optimization-based approaches that involve substantial computational overhead. In this work, we present RoomPainter, a framework that seamlessly integrates efficiency and consistency to achieve high-fidelity texturing of indoor scenes. The core of RoomPainter features a zero-shot technique that effectively adapts a 2D diffusion model for 3D-consistent texture synthesis, along with a two-stage generation strategy that ensures both global and local consistency. Specifically, we introduce Attention-Guided Multi-View Integrated Sampling (MVIS) combined with a neighbor-integrated attention mechanism for zero-shot texture map generation. Using the MVIS, we firstly generate texture map for the entire room to ensure global consistency, then adopt its variant, namely Attention-Guided Multi-View Integrated Repaint Sampling
(MVRS) to repaint individual instances within the room, thereby further enhancing local consistency and addressing the occlusion problem. Experiments demonstrate that RoomPainter achieves superior performance for indoor scene texture synthesis in visual quality, global consistency and generation efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16778 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing Huang, Zhipeng Yu, Wangbo Cheng, Xinhua Zhao, ChengShu Ge, Yunyang Guo, Mingyi Yuan, Li Tian, Yonghong Computer Vision and Pattern Recognition Indoor scene texture synthesis has garnered significant interest due to its important potential applications in virtual reality, digital media and creative arts. Existing diffusion-model-based researches either rely on per-view inpainting techniques, which are plagued by severe cross-view inconsistencies and conspicuous seams, or adopt optimization-based approaches that involve substantial computational overhead. In this work, we present RoomPainter, a framework that seamlessly integrates efficiency and consistency to achieve high-fidelity texturing of indoor scenes. The core of RoomPainter features a zero-shot technique that effectively adapts a 2D diffusion model for 3D-consistent texture synthesis, along with a two-stage generation strategy that ensures both global and local consistency. Specifically, we introduce Attention-Guided Multi-View Integrated Sampling (MVIS) combined with a neighbor-integrated attention mechanism for zero-shot texture map generation. Using the MVIS, we firstly generate texture map for the entire room to ensure global consistency, then adopt its variant, namely Attention-Guided Multi-View Integrated Repaint Sampling (MVRS) to repaint individual instances within the room, thereby further enhancing local consistency and addressing the occlusion problem. Experiments demonstrate that RoomPainter achieves superior performance for indoor scene texture synthesis in visual quality, global consistency and generation efficiency. |
| title | RoomPainter: View-Integrated Diffusion for Consistent Indoor Scene Texturing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.16778 |