通过对比学习提升统一图像修复模型的提示质量，减少冗余并增强任务区分度。
Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration
- 设计稀疏提示模块与对比正则化，分离冗余信息并强化不同退化类型间的边界
- 在五个基准上显著提升现有统一修复模型性能，平均效果达当前最优
- 适合需要处理多种图像退化类型的统一修复系统开发者使用
统一图像修复（AiOIR）需用单一模型应对多种退化类型，其关键挑战在于设计能有效引导修复过程的任务感知提示。现有自适应提示学习易导致任务表征重叠冗余，而基于预训练分类器的显式提示虽提升区分性，却丢失重建所需视觉信息。为此，本文提出对比提示学习（CPL），包含两个互补组件：稀疏提示模块（SPM）高效提取退化感知表征并减少冗余；对比提示正则化（CPR）通过引入跨退化类型的负样本提示，显式强化任务边界。与仅关注退化分类的方法不同，CPL直接优化提示与修复模型间的交互。在五个基准上的实验表明，CPL持续提升强基线模型性能，平均表现达到当前最优，为AiOIR提供通用且鲁棒的解决方案。代码已开源于https://github.com/Aitical/CPLIR。
原文摘要 · Abstract (English)
All-in-One Image Restoration (AiOIR), which addresses diverse degradation types with a unified model, presents significant challenges in designing task-aware prompts that effectively guide restoration across multiple degradation scenarios. While adaptive prompt learning enables end-to-end optimization, it often yields overlapping or redundant task representations. Conversely, explicit prompts derived from pretrained classifiers enhance discriminability but discard critical visual information needed for reconstruction. To address these limitations, we introduce Contrastive Prompt Learning (CPL), a framework that aims to improve prompt-task alignment through two complementary components: a Sparse Prompt Module (SPM) that efficiently captures degradation-aware representations while reducing redundancy, and a Contrastive Prompt Regularization (CPR) that explicitly strengthens task boundaries by incorporating negative prompt samples across different degradation types. Unlike previous approaches that focus primarily on degradation classification, CPL directly optimizes the interaction between prompts and the restoration model. Extensive experiments across five benchmarks show that CPL consistently boosts the performance of strong AiOIR baselines across diverse scenarios. Our approach achieves state-of-the-art average performance on these benchmarks, providing a general and robust solution for AiOIR. The code is available at https://github.com/Aitical/CPLIR
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。