Image blind deblurring networks with back-projection feature fusion

Abstract

： Aiming at the problem of image motion blur caused by hand-held camera jitter and object motion in the process of collecting photos, a generative adversarial network (GAN) based on feature fusion of back projection is proposed for blind image deblurring. Firstly, the generator network is established by using U-Net structure, and a feature fusion residual block based on back projection is designed according to the error feedback principle, which solves the problem of saving spatial information in U-Net structure. Secondly, the self-attention module is introduced into the generator network to extract the feature map that pays more attention to detail. Finally, the combination of perceptual loss, mean square error loss and relative generative adversarial loss effectively alleviates the mode collapse problem of traditional GAN and improves the stability of model training. The experimental results show that the peak signal to noise ratio (PSNR) and structural similarity (SSIM) of this method on GoPro data set are 30.183dB and 0.941 respectively, and 26.962 and 0.837 on the Kohler dataset, with the shortest running time, which are better than the existing mainstream methods. The restored image is clearer in subjective vision and richer in texture details, which can effectively improve the image deblurring effect.