DVANet: Degradation-aware Visual-prior Alignment Network for Image Restoration

2026-06-17

AI Summary

This work addresses the challenge that existing image restoration methods struggle to simultaneously achieve unity, interpretability, and adaptability under complex degradations and localized damage. The authors propose a deep unfolding network based on half-quadratic splitting optimization, which unifies multi-type degradation restoration through iterative collaboration between degradation-aware observation consistency and DINOv3-driven hierarchical visual priors. Key innovations include a degradation representation module that integrates global attributes with local cues, and the embedding of DINOv3 priors into the optimization process to enhance adaptability to unknown degradations and recovery of structural details. Experiments demonstrate that the method achieves state-of-the-art performance across diverse degradation scenarios and cross-domain restoration tasks, exhibiting exceptional generalization capability.

Abstract

All-in-One image restoration aims to develop a unified restoration framework for handling diverse degradation types. Existing end-to-end methods usually regard the restoration process as a black-box mapping, lacking an explicit optimization interpretation. Although deep unfolding provides an interpretable iterative modeling paradigm for image restoration, existing methods mostly rely on fixed degradation assumptions or predefined degradation information, making them difficult to adapt to unified restoration requirements under complex degradations and locally damaged content. This limitation restricts their performance in degradation suppression and structural detail recovery. To address these issues, this paper proposes DVANet, a deep unfolding network inspired by the half-quadratic splitting optimization algorithm, which formulates unified image restoration under complex degradations as a collaborative unfolding process between degradation-aware observation consistency and visual-prior-guided reconstruction. Specifically, in the degradation-aware observation consistency branch, a degradation representation module is employed to extract global degradation attributes and local degradation cues, and degradation-conditioned mapping is used to enhance the model's adaptability to different degradation types. In the visual-prior-guided reconstruction branch, DINOv3 is introduced to provide structural and semantic information as hierarchical visual priors, thereby complementing the missing structural information in damaged regions and improving detail recovery. Extensive experiments demonstrate that DVANet achieves superior or competitive performance on multi-scenario degradation and cross-domain image restoration tasks, showing favorable degradation adaptability and generalization ability.

Problem

• image restoration
• complex degradations
• unified framework
• degradation adaptability
• structural detail recovery

Innovation

• Degradation-aware
• Deep unfolding
• Visual prior
• DINOv3
• Unified image restoration