Dynamic Degradation Decomposition Network for All-in-One Image Restoration

TL;DR

This paper introduces D$^3$Net, a dynamic, prompt-guided network that adaptively restores images degraded by various unknown types, outperforming existing methods in flexibility and restoration quality.

Contribution

The paper proposes a novel degradation decomposition network with cross-domain interaction and prompt-based dynamic decomposition for all-in-one image restoration.

Findings

Outperforms state-of-the-art methods in multiple restoration tasks.

Achieves significant PSNR improvements on benchmark datasets.

Demonstrates effective handling of unknown and complex degradations.

Abstract

Currently, restoring clean images from a variety of degradation types using a single model is still a challenging task. Existing all-in-one image restoration approaches struggle with addressing complex and ambiguously defined degradation types. In this paper, we introduce a dynamic degradation decomposition network for all-in-one image restoration, named D$^3$Net. D$^3$Net achieves degradation-adaptive image restoration with guided prompt through cross-domain interaction and dynamic degradation decomposition. Concretely, in D$^3$Net, the proposed Cross-Domain Degradation Analyzer (CDDA) engages in deep interaction between frequency domain degradation characteristics and spatial domain image features to identify and model variations of different degradation types on the image manifold, generating degradation correction prompt and strategy prompt, which guide the following decomposition process. Furthermore, the prompt-based Dynamic Decomposition Mechanism (DDM) for progressive degradation decomposition, that encourages the network to adaptively select restoration strategies utilizing the two-level prompt generated by CDDA. Thanks to the synergistic cooperation between CDDA and DDM, D$^3$Net achieves superior flexibility and scalability in handling unknown degradation, while effectively reducing unnecessary computational overhead. Extensive experiments on multiple image restoration tasks demonstrate that D$^3$Net significantly outperforms the state-of-the-art approaches, especially improving PSNR by 5.47dB and 3.30dB on the SOTS-Outdoor and GoPro datasets, respectively.