paper-with-me

홈 › Papers

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

2026-05-21 · Feng Zhu, Shuyang Xie, Yihan Zeng, Ming Liu, Wangmeng Zuo arxiv

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.

📄 PDF Abstract BibTeX arXiv:2605.22104

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningImage Restoration

Similar Papers 제목 키워드 기반

Causal-AgentIR: Self-Evolving Causal Memory for Adaptive Image Restoration Agents

2026-07-23 · Hu Gao, Yulong Chen, Lizhuang Ma arxiv

Image restoration agents have recently emerged as a flexible paradigm for handling diverse and unpredictable degradations in real-world scenarios. Existing agents typically formulate restoration as a tool-using process, …

Image Restoration

Hybrid Agents for Image Restoration

2025-03-13 · Bingchen Li, Xin Li, Yiting Lu, Zhibo Chen

Existing Image Restoration (IR) studies typically focus on task-specific or universal modes individually, relying on the mode selection of users and lacking the cooperation between multiple task-specific/universal restor…

Image RestorationIn-Context LearningLanguage ModelingLanguage Modelling+3

Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution

2026-06-27 · Shuang Cui, Fan Ji, Guanglong Sun, Yufei Guo 외 arxiv

Real-world image restoration (IR) remains challenging due to complex and coupled degradations. While recent agentic IR frameworks leverage Large Language Models for flexible tool planning, they face two critical limitati…

Image Restoration

Restore-R1: Efficient Image Restoration Agents via Reinforcement Learning with Multimodal LLM Perceptual Feedback

2025-12-21 · Jianglin Lu, Yuanwei Wu, Ziyi Zhao, Hongcheng Wang 외 arxiv

Complex image restoration aims to recover high-quality images from inputs affected by multiple degradations such as blur, noise, rain, and compression artifacts. Recent restoration agents, powered by vision-language mode…

Reinforcement LearningImage Restoration

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

2026-03-12 · Zhaocheng Yu, Xiang Chen, Runzhe Li, Zihan Geng 외 arxiv

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…

Image Restoration