Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Huiqiang, Song, Mingchen, Zhong, Guoqiang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2502.19068
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916646756548608
author Wang, Huiqiang
Song, Mingchen
Zhong, Guoqiang
author_facet Wang, Huiqiang
Song, Mingchen
Zhong, Guoqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dynamic Degradation Decomposition Network for All-in-One Image Restoration
Wang, Huiqiang
Song, Mingchen
Zhong, Guoqiang
Computer Vision and Pattern Recognition
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.
title Dynamic Degradation Decomposition Network for All-in-One Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.19068