AI 中文总结
针对一体化图像修复现有方法的结构扭曲与语义不一致问题，提出双先验协同网络DPC-Net，联合利用退化-语义耦合与低层视觉先验，在多基准上实现优于现有最优方法的修复性能。
AI 中文摘要
一体化图像修复（AiOIR）旨在用统一模型处理多种类型的图像退化问题。然而，现有方法在退化建模中常忽略图像语义，且重建阶段缺乏低层视觉先验，导致结构扭曲和语义不一致。为解决这些问题，我们提出一种新型双先验协同网络（DPC-Net），通过联合利用退化-语义耦合先验和低层视觉先验实现高质量修复。具体而言，将退化图像输入退化感知网络（DAN）以提取退化-语义耦合特征；为此，视觉语言模型（VLM）通过约束其特征分布来监督DAN，将图像语义引入退化模式的编码过程；退化-语义调制模块（DSMM）进一步将该指导转化为退化-语义耦合关系，并将耦合表示传播至解码器。解码阶段，知识库提供低层视觉先验，双先验协同重建模块（DPCR）整合双先验信息，在指导退化去除的同时保留结构与语义，生成高保真修复图像。在多个修复基准上开展的大量实验表明，DPC-Net相较于现有最优AiOIR方法取得了更优性能。
英文摘要
All-in-One Image Restoration (AiOIR) aims to handle diverse degradations within a unified model. However, existing methods often overlook image semantics in degradation modeling and lack low-level visual priors during reconstruction, leading to structural distortions and semantic inconsistencies. To address these issues, we propose a novel Dual-Prior Collaborative Network (DPC-Net), which achieves high-quality restoration by jointly exploiting degradation-semantic coupled priors and low-level visual priors. Specifically, degraded images are fed into a Degradation-Aware Network (DAN) to extract degradation-semantic coupled features. To this end, a Vision-Language Model (VLM) supervises DAN by constraining its features distribution, introducing image semantics into the encoding of degradation patterns. A Degradation-Semantic Modulation Module (DSMM) further translates this guidance into degradation-semantic coupling and propagates coupled representations to the decoder. During decoding, knowledge bases provide low-level visual priors, and the Dual-Prior Collaborative Reconstruction Module (DPCR) integrates dual-prior information to guide degradation removal while preserving structure and semantics, producing high-fidelity restored images. Extensive experiments on multiple restoration benchmarks demonstrate that DPC-Net achieves superior performance against state-of-the-art AiOIR methods.
