Non-blind deconvolution has been an active challenge in the research fields of computer vision and computational photography. However, most existing deblurring methods conduct direct deconvolution only on the degraded image and are sensitive to noise. To enhance the performance of non-blind deconvolution, we propose a novel framework method by exploiting different sparse priors of subspace imag...

Blurred iris images are inevitable during iris image acquisition due to limited depth of field and movement of subjects. The blurred iris images lose detailed texture information for accurate identity verification, so this paper proposes a novel iris image deblurring method to enhance the quality of blurred iris images. Our method makes full use of the prior information of iris images. Firstly,...

The moving image deblurring method based on deep learning has achieved good results. However, some methods are not effective in restoring texture detail information. Therefore, this paper proposes a High-Frequency Attention Residual Module (HFAR), which is used to guide the network learn more high-frequency information improve quality of restoration. designed attention residual module consists ...