DPC-Net: Dual-Prior Collaborative Network for All-in-One Image Restoration

2026-08-20

AI Summary

为解决图像复原中结构失真和语义不一致问题，提出DPC-Net，通过结合退化-语义耦合先验和低级视觉先验实现高质量图像复原。

Abstract

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.

Problem

• Image Restoration
• Degradation Modeling
• Visual Priors
• Structural Distortions
• Semantic Inconsistencies

Innovation

• Dual-Prior Collaborative Network
• Degradation-Semantic Coupled Priors
• Low-Level Visual Priors
• Vision-Language Model
• Degradation-Aware Network