OPERA: An Agent for Image Restoration with End-to-End Joint Planning-Execution Optimization

TL;DR

OPERA is an end-to-end framework that jointly optimizes image restoration planning and tool execution using reinforcement learning and cooperative tool training, significantly improving performance on complex degradation tasks.

Contribution

It introduces a novel joint optimization approach for planning and executing image restoration, overcoming limitations of previous agent-based methods.

Findings

OPERA outperforms existing methods on multi-degradation benchmarks.

The framework achieves superior restoration quality on real-world datasets.

Joint optimization enhances cooperation among restoration tools.

Abstract

Real-world image restoration is challenging due to complex and interacting mixed degradations. Recent agent-based approaches address this problem by composing multiple task-specific restoration tools. However, empirical analysis reveals that their performance is fundamentally limited by implicitly constrained planning spaces and the lack of coordination among independently pretrained tools. To address these issues, we propose OPERA (Optimized Planning-Execution Restoration Agent), a framework that jointly optimizes restoration planning and tool execution in an end-to-end manner. On the planning side, OPERA uses reinforcement learning to directly optimize tool composition over a combinatorial plan space, with the final restoration quality as the reward. On the execution side, OPERA introduces agent-guided co-training of restoration tools, enabling them to learn cooperative behaviors under sequential composition. Extensive experiments on multi-degradation benchmarks and real-world datasets demonstrate that OPERA consistently outperforms both all-in-one restoration models and existing agent-based methods across diverse and complex degradation scenarios.