Hybrid U-shaped network and Transformer for image deblurring
To address the problem that existing deblurring methods cannot effectively restore fine de-tails of images,an image deblurring method combining a U-shaped network and Transformer is pro-posed.Firstly,a multi-scale feature extraction module is used to extract shallow feature information from the image.Then,a hierarchical nested U-shaped subnet with a stepwise feature enhancement mod-ule is employed to obtain deep feature information while preserving image detail information.Next,a local-global residual refinement module is constructed,which fully extracts global and local information through information interaction between convolutional neural networks and Swin Transformer,and fur-ther refines the feature information.Finally,a 1×1 convolutional layer is used for feature reconstruc-tion.The proposed method achieves a peak signal-to-noise ratio(PSNR)of 32.92 and a structural simi-larity index mean(SSIM)of 0.964 on the GoPro dataset,both outperforming other comparative meth-ods.Experimental results demonstrate that the proposed method can effectively remove blur and recon-struct a potentially clear image with rich details.
万方数据
维普
