Frequency-domain Learning with Kernel Prior for Blind Image Deblurring
This addresses the problem of poor generalization in image deblurring for computer vision applications, representing an incremental improvement by integrating traditional priors into deep learning.
The paper tackles the limited generalization of deep learning methods for blind image deblurring by introducing a kernel prior and a Frequency Integration Module, resulting in outperforming state-of-the-art methods on multiple tasks with robust generalization.
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.