Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
This addresses a practical issue for applications like autonomous driving or photography where image clarity through windows in rainy conditions is crucial, representing a novel task definition rather than an incremental improvement.
The paper tackles the problem of removing both raindrops and reflections from images captured through glass surfaces, a composite degradation previously unaddressed, and proposes a diffusion-based framework that achieves state-of-the-art performance on a new real-shot benchmark and in-the-wild images.
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.