Frequency-domain Learning with Kernel Prior for Blind Image Deblurring

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sun, Jixiang, Lei, Fei, Zhang, Jiawei, Sun, Wenxiu, Yang, Yujiu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909586105040896
author Sun, Jixiang
Lei, Fei
Zhang, Jiawei
Sun, Wenxiu
Yang, Yujiu
author_facet Sun, Jixiang
Lei, Fei
Zhang, Jiawei
Sun, Wenxiu
Yang, Yujiu
contents While achieving excellent results on various datasets, many deep learning methods for image deblurring suffer from limited generalization capabilities with out-of-domain data. This limitation is likely caused by their dependence on certain domain-specific datasets. To address this challenge, we argue that it is necessary to introduce the kernel prior into deep learning methods, as the kernel prior remains independent of the image context. For effective fusion of kernel prior information, we adopt a rational implementation method inspired by traditional deblurring algorithms that perform deconvolution in the frequency domain. We propose a module called Frequency Integration Module (FIM) for fusing the kernel prior and combine it with a frequency-based deblurring Transfomer network. Experimental results demonstrate that our method outperforms state-of-the-art methods on multiple blind image deblurring tasks, showcasing robust generalization abilities. Source code will be available soon.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Frequency-domain Learning with Kernel Prior for Blind Image Deblurring
Sun, Jixiang
Lei, Fei
Zhang, Jiawei
Sun, Wenxiu
Yang, Yujiu
Computer Vision and Pattern Recognition
While achieving excellent results on various datasets, many deep learning methods for image deblurring suffer from limited generalization capabilities with out-of-domain data. This limitation is likely caused by their dependence on certain domain-specific datasets. To address this challenge, we argue that it is necessary to introduce the kernel prior into deep learning methods, as the kernel prior remains independent of the image context. For effective fusion of kernel prior information, we adopt a rational implementation method inspired by traditional deblurring algorithms that perform deconvolution in the frequency domain. We propose a module called Frequency Integration Module (FIM) for fusing the kernel prior and combine it with a frequency-based deblurring Transfomer network. Experimental results demonstrate that our method outperforms state-of-the-art methods on multiple blind image deblurring tasks, showcasing robust generalization abilities. Source code will be available soon.
title Frequency-domain Learning with Kernel Prior for Blind Image Deblurring
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.14664