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

2026-03-12

AI Summary

Existing image deraining methods predominantly rely on static inference paradigms, which struggle to handle the complex, coupled degradations—such as noise, blur, and color distortion—in real-world rainy images, often yielding artifacts and inconsistent perceptual quality. This work proposes a plug-and-play agent-based deraining framework that introduces an agent mechanism into this task for the first time. By employing a planning network to dynamically schedule an optimal sequence of restoration tools and integrating an intensity modulation mechanism for spatially adaptive refinement, the approach transforms deraining from a static process into dynamic, intelligent decision-making. Without requiring iterative search, the method accurately corrects residual errors and significantly enhances the performance of multiple state-of-the-art models on both synthetic and real rainy image datasets, demonstrating strong generalization and consistently high-quality restoration.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Diffusion Models for Vision
• Multiagent Systems: Multiagent Planning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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.

Problem

• single-image deraining
• complex degradations
• residual artifacts
• perceptual quality
• real-world rain

Innovation

• plug-and-play
• agent-based restoration
• planning network
• strength modulation
• adaptive deraining