Derain-Agent: A Plug-and-Play Agent Framework for Rainy Image Restoration

TL;DR

Derain-Agent introduces a flexible, agent-based framework that enhances existing rain removal models by adaptively scheduling and applying restoration tools for improved, region-specific image quality in rainy images.

Contribution

It proposes a novel plug-and-play agent framework with planning and strength modulation mechanisms for dynamic, adaptive rain image restoration.

Findings

Boosts performance of state-of-the-art deraining models

Achieves superior results on synthetic and real-world benchmarks

Reduces residual artifacts and improves perceptual quality

Abstract

While deep learning has advanced single-image deraining, existing models suffer from a fundamental limitation: they employ a static inference paradigm that fails to adapt to the complex, coupled degradations (e.g., noise artifacts, blur, and color deviation) of real-world rain. Consequently, restored images often exhibit residual artifacts and inconsistent perceptual quality. In this work, we present Derain-Agent, a plug-and-play refinement framework that transitions deraining from static processing to dynamic, agent-based restoration. Derain-Agent equips a base deraining model with two core capabilities: 1) a Planning Network that intelligently schedules an optimal sequence of restoration tools for each instance, and 2) a Strength Modulation mechanism that applies these tools with spatially adaptive intensity. This design enables precise, region-specific correction of residual errors without the prohibitive cost of iterative search. Our method demonstrates strong generalization, consistently boosting the performance of state-of-the-art deraining models on both synthetic and real-world benchmarks.