Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.17347 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912714191798272 |
|---|---|
| author | Hu, Jichen Yang, Chen Zhou, Zanwei Fang, Jiemin Yang, Xiaokang Tian, Qi Shen, Wei |
| author_facet | Hu, Jichen Yang, Chen Zhou, Zanwei Fang, Jiemin Yang, Xiaokang Tian, Qi Shen, Wei |
| contents | Reflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections. Despite significant progress, existing methods are hindered by the scarcity of high-quality, diverse data and insufficient restoration priors, resulting in limited generalization across various real-world scenarios. In this paper, we propose Dereflection Any Image, a comprehensive solution with an efficient data preparation pipeline and a generalizable model for robust reflection removal. First, we introduce a dataset named Diverse Reflection Removal (DRR) created by randomly rotating reflective mediums in target scenes, enabling variation of reflection angles and intensities, and setting a new benchmark in scale, quality, and diversity. Second, we propose a diffusion-based framework with one-step diffusion for deterministic outputs and fast inference. To ensure stable learning, we design a three-stage progressive training strategy, including reflection-invariant finetuning to encourage consistent outputs across varying reflection patterns that characterize our dataset. Extensive experiments show that our method achieves SOTA performance on both common benchmarks and challenging in-the-wild images, showing superior generalization across diverse real-world scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17347 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dereflection Any Image with Diffusion Priors and Diversified Data Hu, Jichen Yang, Chen Zhou, Zanwei Fang, Jiemin Yang, Xiaokang Tian, Qi Shen, Wei Computer Vision and Pattern Recognition Reflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections. Despite significant progress, existing methods are hindered by the scarcity of high-quality, diverse data and insufficient restoration priors, resulting in limited generalization across various real-world scenarios. In this paper, we propose Dereflection Any Image, a comprehensive solution with an efficient data preparation pipeline and a generalizable model for robust reflection removal. First, we introduce a dataset named Diverse Reflection Removal (DRR) created by randomly rotating reflective mediums in target scenes, enabling variation of reflection angles and intensities, and setting a new benchmark in scale, quality, and diversity. Second, we propose a diffusion-based framework with one-step diffusion for deterministic outputs and fast inference. To ensure stable learning, we design a three-stage progressive training strategy, including reflection-invariant finetuning to encourage consistent outputs across varying reflection patterns that characterize our dataset. Extensive experiments show that our method achieves SOTA performance on both common benchmarks and challenging in-the-wild images, showing superior generalization across diverse real-world scenes. |
| title | Dereflection Any Image with Diffusion Priors and Diversified Data |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.17347 |