Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.08299 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913887275712512 |
|---|---|
| author | Yang, Kangning Ouyang, Ling Sun, Huiming Cai, Jie Fu, Lan Ding, Jiaming Ho, Chiu Man Meng, Zibo |
| author_facet | Yang, Kangning Ouyang, Ling Sun, Huiming Cai, Jie Fu, Lan Ding, Jiaming Ho, Chiu Man Meng, Zibo |
| contents | Reflection removal technology plays a crucial role in photography and computer vision applications. However, existing techniques are hindered by the lack of high-quality in-the-wild datasets. In this paper, we propose a novel paradigm for collecting reflection datasets from a fresh perspective. Our approach is convenient, cost-effective, and scalable, while ensuring that the collected data pairs are of high quality, perfectly aligned, and represent natural and diverse scenarios. Following this paradigm, we collect a Real-world, Diverse, and Pixel-aligned dataset (named OpenRR-1k dataset), which contains 1,000 high-quality transmission-reflection image pairs collected in the wild. Through the analysis of several reflection removal methods and benchmark evaluation experiments on our dataset, we demonstrate its effectiveness in improving robustness in challenging real-world environments. Our dataset is available at https://github.com/caijie0620/OpenRR-1k. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08299 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpenRR-1k: A Scalable Dataset for Real-World Reflection Removal Yang, Kangning Ouyang, Ling Sun, Huiming Cai, Jie Fu, Lan Ding, Jiaming Ho, Chiu Man Meng, Zibo Computer Vision and Pattern Recognition Reflection removal technology plays a crucial role in photography and computer vision applications. However, existing techniques are hindered by the lack of high-quality in-the-wild datasets. In this paper, we propose a novel paradigm for collecting reflection datasets from a fresh perspective. Our approach is convenient, cost-effective, and scalable, while ensuring that the collected data pairs are of high quality, perfectly aligned, and represent natural and diverse scenarios. Following this paradigm, we collect a Real-world, Diverse, and Pixel-aligned dataset (named OpenRR-1k dataset), which contains 1,000 high-quality transmission-reflection image pairs collected in the wild. Through the analysis of several reflection removal methods and benchmark evaluation experiments on our dataset, we demonstrate its effectiveness in improving robustness in challenging real-world environments. Our dataset is available at https://github.com/caijie0620/OpenRR-1k. |
| title | OpenRR-1k: A Scalable Dataset for Real-World Reflection Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.08299 |