提出可扩展可控的通用图像修复框架，解决多退化场景下模型失真问题。
UnSCAR: Universal, Scalable, Controllable, and Adaptable Image Restoration
- 采用多分支专家混合架构，分离不同退化类型的修复知识。
- 支持超16种退化类型，对未见退化域仍保持强泛化能力。
- 用户可自由控制修复方向，适用于多种真实图像恢复场景。
通用图像修复旨在使用单一推理模型从各种现实退化中恢复干净图像。尽管进展显著，现有全功能修复网络难以扩展至多种退化类型。随着退化种类增加，训练变得不稳定，模型规模急剧膨胀，且在已见与未见退化域上性能均下降。本文指出，规模化受限于联合学习中退化间的干扰，导致灾难性遗忘。为此，我们提出统一推理流程与多分支专家混合架构，将修复知识分解至任务自适应的专业专家中。该方法实现超16种退化类型的可扩展学习，对未见退化域具有稳健适应性，并支持用户可控的跨退化修复。实验表明，其在多个基准上表现优异，为可扩展、可控的通用图像修复确立了新范式。
原文摘要 · Abstract (English)
Universal image restoration aims to recover clean images from arbitrary real-world degradations using a single inference model. Despite significant progress, existing all-in-one restoration networks do not scale to multiple degradations. As the number of degradations increases, training becomes unstable, models grow excessively large, and performance drops across both seen and unseen domains. In this work, we show that scaling universal restoration is fundamentally limited by interference across degradations during joint learning, leading to catastrophic task forgetting. To address this challenge, we introduce a unified inference pipeline with a multi-branch mixture-of-experts architecture that decomposes restoration knowledge across specialized task-adaptable experts. Our approach enables scalable learning (over sixteen degradations), adapts and generalizes robustly to unseen domains, and supports user-controllable restoration across degradations. Beyond achieving superior performance across benchmarks, this work establishes a new design paradigm for scalable and controllable universal image restoration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。