Pixel-wise Contrastive Learning for Single Image Super-resolution
Deep convolutional neural network(CNN)has achieved great success in single image super-resolution(SISR).However,SISR is still an open issue,and reconstructed super-resolution(SR)images often suffer from blur-ring,loss of texture details and distortion.In this paper,a new pixel-wise contrastive loss is proposed to improve the fidelity and visual quality of SR images by making the pixels of SR images as close as possible to the corres-ponding pixels of the original high-resolution(HR)images and away from the other pixels in the local region.We also propose a progressive residual feature fusion network(PRFFN)with combined contrastive loss,and the main contributions include:1)A general pixel-wise loss function based on contrastive learning is proposed,which can im-prove the fidelity and visual quality of SR images;2)A lightweight multi-scale residual channel attention block(MRCAB)is proposed,which can better extract and utilize multi-scale feature information;3)A spatial attention fusion block(SAFB)is proposed,which can better utilize the correlation of neighboring spatial features.The experi-mental results demonstrate that PRFFN significantly outperforms other representative methods.
万方数据
维普
