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

2026-03-17

AI Summary

This work addresses the challenging problem of image degradation caused by the coexistence of raindrops and reflections when capturing scenes through glass in rainy conditions—a composite interference that existing methods struggle to handle effectively. To tackle this issue, the paper formally defines a novel joint raindrop and reflection removal task (UR³), introduces RDRF, a high-quality real-world dataset comprising aligned image pairs, and proposes DiffUR³, a diffusion-based framework that unifies the modeling and simultaneous removal of both degradations. By incorporating generative priors and task-specific architectural designs, DiffUR³ achieves state-of-the-art performance, significantly outperforming current raindrop removal, reflection removal, and unified approaches on both the RDRF benchmark and complex in-the-wild images.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• raindrops
• reflections
• image degradation
• visibility reduction
• composite degradation

Innovation

• unified removal
• diffusion model
• raindrop removal
• reflection removal
• benchmark dataset