Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jiang, Xu, Li, Gehui, Chen, Bin, Zhang, Jian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.09403
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912278329163776
author Jiang, Xu
Li, Gehui
Chen, Bin
Zhang, Jian
author_facet Jiang, Xu
Li, Gehui
Chen, Bin
Zhang, Jian
contents Image restoration (IR) is challenging due to the complexity of real-world degradations. While many specialized and all-in-one IR models have been developed, they fail to effectively handle complex, mixed degradations. Recent agentic methods RestoreAgent and AgenticIR leverage intelligent, autonomous workflows to alleviate this issue, yet they suffer from suboptimal results and inefficiency due to their resource-intensive finetunings, and ineffective searches and tool execution trials for satisfactory outputs. In this paper, we propose MAIR, a novel Multi-Agent approach for complex IR problems. We introduce a real-world degradation prior, categorizing degradations into three types: (1) scene, (2) imaging, and (3) compression, which are observed to occur sequentially in real world, and reverse them in the opposite order. Built upon this three-stage restoration framework, MAIR emulates a team of collaborative human specialists, including a "scheduler" for overall planning and multiple "experts" dedicated to specific degradations. This design minimizes search space and trial efforts, improving image quality while reducing inference costs. In addition, a registry mechanism is introduced to enable easy integration of new tools. Experiments on both synthetic and real-world datasets show that proposed MAIR achieves competitive performance and improved efficiency over the previous agentic IR system. Code and models will be made available.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09403
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Agent Image Restoration
Jiang, Xu
Li, Gehui
Chen, Bin
Zhang, Jian
Computer Vision and Pattern Recognition
Artificial Intelligence
Image restoration (IR) is challenging due to the complexity of real-world degradations. While many specialized and all-in-one IR models have been developed, they fail to effectively handle complex, mixed degradations. Recent agentic methods RestoreAgent and AgenticIR leverage intelligent, autonomous workflows to alleviate this issue, yet they suffer from suboptimal results and inefficiency due to their resource-intensive finetunings, and ineffective searches and tool execution trials for satisfactory outputs. In this paper, we propose MAIR, a novel Multi-Agent approach for complex IR problems. We introduce a real-world degradation prior, categorizing degradations into three types: (1) scene, (2) imaging, and (3) compression, which are observed to occur sequentially in real world, and reverse them in the opposite order. Built upon this three-stage restoration framework, MAIR emulates a team of collaborative human specialists, including a "scheduler" for overall planning and multiple "experts" dedicated to specific degradations. This design minimizes search space and trial efforts, improving image quality while reducing inference costs. In addition, a registry mechanism is introduced to enable easy integration of new tools. Experiments on both synthetic and real-world datasets show that proposed MAIR achieves competitive performance and improved efficiency over the previous agentic IR system. Code and models will be made available.
title Multi-Agent Image Restoration
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2503.09403