一个模型搞定多种图像修复，速度还快，效果顶尖。
DRNet: All-in-One Image Restoration via Prior-Guided Dynamic Reparameterization
- 用动态重参数化机制避免每张图都重新计算，提速降耗。
- 五项修复任务均达顶尖水平，参数量小但性能强。
- 既可盲修通用图像，也能按用户需求做专项修复。
全功能图像修复旨在单一模型中处理多种退化问题。然而现有方法常面临三大挑战：1）动态退化估计导致每输入计算开销大；2）任务异质性引发优化困难；3）编码器设计低效且频率无关。为此，我们提出动态重参数化网络（DRNet），基于初始化阶段重构范式，从根本上消除每输入的计算开销。核心是受任务特定调制器（TSM）引导的动态重参数化MLP（DRMLP），通过统一架构协调特定修复目标与通用模式，有效缓解任务异质性。此外，引入连续小波变换编码器（CWTE），通过小波分解显式利用频率特性，实现轻量而强大的设计。大量实验表明，DRNet在五项修复任务上均达到领先性能，且参数效率优异。关键优势在于独特灵活性：既能作为盲修复的高性能基础模型，也可作为顶尖的用户引导专用模型表现卓越。
原文摘要 · Abstract (English)
All-in-one image restoration aims to handle diverse degradations within a single model. However, existing methods often suffer from three key limitations: 1) per-input computational overhead from dynamic degradation estimation; 2) optimization challenges due to task heterogeneity; and 3) inefficient, frequency-agnostic encoder designs. To overcome these, we introduce the Dynamic Reparameterization Network (DRNet), a novel framework operating on an initialization-stage reconfiguration paradigm that fundamentally eliminates per-input overhead. At its core, a Dynamic Reparameterization MLP (DRMLP) guided by a Task-Specific Modulator (TSM), which effectively mitigates task heterogeneity by orchestrating both specific restoration goals and a versatile general-purpose mode within a unified architecture. Furthermore, we incorporate a Continuous Wavelet Transform Encoder (CWTE) that explicitly leverages frequency characteristics via wavelet decomposition for a lightweight yet powerful design. Extensive experiments demonstrate that DRNet achieves state-of-the-art performance across five restoration tasks with superior parameter efficiency. Crucially, it showcases unique flexibility, excelling as both a highly competitive foundation model for blind restoration and a top-performing user-guided specialist.
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。