Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline

TL;DR

This paper introduces a new benchmark dataset and a diffusion-based method for jointly removing raindrops and reflections from images, addressing a practical problem with a novel unified approach.

Contribution

It formally defines the combined raindrop and reflection removal task, creates a high-quality dataset, and proposes a diffusion-based framework that outperforms existing methods.

Findings

Our method achieves state-of-the-art results on the new benchmark.

The RDRF dataset provides diverse, high-quality image pairs for this task.

DiffUR$^3$ effectively removes both raindrops and reflections in challenging images.

Abstract

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.