Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.04501 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915184352690176 |
|---|---|
| author | Shi, Zhihao Huo, Dong Zhou, Yuhongze Yin, Kejia Min, Yan Lu, Juwei Zuo, Xinxin |
| author_facet | Shi, Zhihao Huo, Dong Zhou, Yuhongze Yin, Kejia Min, Yan Lu, Juwei Zuo, Xinxin |
| contents | Current 3D inpainting and object removal methods are largely limited to front-facing scenes, facing substantial challenges when applied to diverse, "unconstrained" scenes where the camera orientation and trajectory are unrestricted. To bridge this gap, we introduce a novel approach that produces inpainted 3D scenes with consistent visual quality and coherent underlying geometry across both front-facing and unconstrained scenes. Specifically, we propose a robust 3D inpainting pipeline that incorporates geometric priors and a multi-view refinement network trained via test-time adaptation, building on a pre-trained image inpainting model. Additionally, we develop a novel inpainting mask detection technique to derive targeted inpainting masks from object masks, boosting the performance in handling unconstrained scenes. To validate the efficacy of our approach, we create a challenging and diverse benchmark that spans a wide range of scenes. Comprehensive experiments demonstrate that our proposed method substantially outperforms existing state-of-the-art approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_04501 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement Shi, Zhihao Huo, Dong Zhou, Yuhongze Yin, Kejia Min, Yan Lu, Juwei Zuo, Xinxin Computer Vision and Pattern Recognition Current 3D inpainting and object removal methods are largely limited to front-facing scenes, facing substantial challenges when applied to diverse, "unconstrained" scenes where the camera orientation and trajectory are unrestricted. To bridge this gap, we introduce a novel approach that produces inpainted 3D scenes with consistent visual quality and coherent underlying geometry across both front-facing and unconstrained scenes. Specifically, we propose a robust 3D inpainting pipeline that incorporates geometric priors and a multi-view refinement network trained via test-time adaptation, building on a pre-trained image inpainting model. Additionally, we develop a novel inpainting mask detection technique to derive targeted inpainting masks from object masks, boosting the performance in handling unconstrained scenes. To validate the efficacy of our approach, we create a challenging and diverse benchmark that spans a wide range of scenes. Comprehensive experiments demonstrate that our proposed method substantially outperforms existing state-of-the-art approaches. |
| title | IMFine: 3D Inpainting via Geometry-guided Multi-view Refinement |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.04501 |