Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911583643369472 |
|---|---|
| author | Liu, Xingyu He, Zewei Chen, Yu Zhu, Chunyu Chen, Zixuan Luo, Xing Lu, Zhe-Ming |
| author_facet | Liu, Xingyu He, Zewei Chen, Yu Zhu, Chunyu Chen, Zixuan Luo, Xing Lu, Zhe-Ming |
| contents | When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images. The RDRF dataset and the codes will be made public upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16446 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline Liu, Xingyu He, Zewei Chen, Yu Zhu, Chunyu Chen, Zixuan Luo, Xing Lu, Zhe-Ming Computer Vision and Pattern Recognition When capturing images through glass surfaces or windshields on rainy days, raindrops and reflections frequently co-occur to significantly reduce the visibility of captured images. This practical problem lacks attention and needs to be resolved urgently. Prior de-raindrop, de-reflection, and all-in-one models have failed to address this composite degradation. To this end, we first formally define the unified removal of raindrops and reflections (UR$^3$) task for the first time and construct a real-shot dataset, namely RainDrop and ReFlection (RDRF), which provides a new benchmark with substantial, high-quality, diverse image pairs. Then, we propose a novel diffusion-based framework (i.e., DiffUR$^3$) with several target designs to address this challenging task. By leveraging the powerful generative prior, DiffUR$^3$ successfully removes both types of degradations. Extensive experiments demonstrate that our method achieves state-of-the-art performance on our benchmark and on challenging in-the-wild images. The RDRF dataset and the codes will be made public upon acceptance. |
| title | Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.16446 |