Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

TL;DR

This paper introduces a novel cross-scenario deraining adaptation framework that uses unpaired data, superpixel structural priors, and multi-stage pseudo-rain synthesis to improve real-world rain removal performance without requiring paired rainy images.

Contribution

It proposes a pioneering adaptation framework that leverages unpaired data and structural priors, enabling effective deraining across diverse scenarios without target domain paired samples.

Findings

Achieves up to 59% PSNR improvement in OOD domains.

Significantly accelerates training convergence.

Demonstrates compatibility with various deraining architectures.

Abstract

Image deraining plays a pivotal role in low-level computer vision, serving as a prerequisite for robust outdoor surveillance and autonomous driving systems. While deep learning paradigms have achieved remarkable success in firmly aligned settings, they often suffer from severe performance degradation when generalized to unseen Out-of-Distribution (OOD) scenarios. This failure stems primarily from the significant domain discrepancy between synthetic training datasets and the complex physical dynamics of real-world rain. To address these challenges, this paper proposes a pioneering cross-scenario deraining adaptation framework. Diverging from conventional approaches, our method obviates the requirements for paired rainy observations in the target domain, leveraging exclusively rain-free background images. We design a Superpixel Generation (Sup-Gen) module to extract stable structural priors from the source domain using Simple Linear Iterative Clustering. Subsequently, a Resolution-adaptive Fusion strategy is introduced to align these source structures with target backgrounds through texture similarity, ensuring the synthesis of diverse and realistic pseudo-data. Finally, we implement a pseudo-label re-Synthesize mechanism that employs multi-stage noise generation to simulate realistic rain streaks. This framework functions as a versatile plug-and-play module capable of seamless integration into arbitrary deraining architectures. Extensive experiments on state-of-the-art models demonstrate that our approach yields remarkable PSNR gains of up to 32% to 59% in OOD domains while significantly accelerating training convergence.