提出新任务与数据集，用扩散模型同时清除雨滴和反光。
Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
- 设计基于扩散的统一框架，联合处理雨滴与反光。
- 在自建数据集RDRF上达到当前最佳性能。
- 适合图像增强、自动驾驶等真实场景应用。
雨天通过玻璃或挡风玻璃拍摄时，雨滴与反光常同时出现，严重降低图像可见性。现有去雨滴、去反光及一体化模型均无法解决此类复合退化问题。为此，首次正式定义统一去除雨滴与反光（UR³）任务，并构建真实拍摄数据集RDRF，包含大量高质量、多样化的图像对，提供新基准。提出基于扩散的新型框架DiffUR³，通过目标设计利用强大生成先验，有效消除两类退化。大量实验证明，该方法在所提基准及野外复杂图像上均达领先性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。