Transformer-Based Super-Resolution Reconstruction of Dongba Paintings
Naxi Dongba paintings have complex lines and rich colors.Directly using the existing methods to perform super-resolution reconstruction of low-resolution Dongba painting images in real scenes has prob-lems such as unclear lines,excessive smoothness in local areas and lack of details.To solve the above prob-lems,we propose a Transformer-based super-resolution reconstruction method for Dongba paintings.Firstly,the generator uses a convolutional layer and the residual dense Swin Transformer blocks to extract the shal-low and deep features of the Dongba painting image,and fuses the features through the reconstruction mod-ule to reconstruct a high-resolution image.Secondly,the discriminator uses U-Net to evaluate the realness of each pixel to enhance the texture details of the reconstructed image.Finally,the generator is trained using pixel loss,perceptual loss and adversarial loss to generate natural and clear Dongba painting images.Com-pared with the other 8 methods on the self-built Dongba painting testing set,the results show that the recon-struction results of the proposed method have better visual effects.The average PIQE is 22.7493,20.2649 and 18.3780,and the average ENIQA is 0.0917,0.0639 and 0.0684 at magnifications of 2×,4×,and 8×,respectively,all of which are superior to other methods.The proposed method has good scalability and achieves clearer results on natural images as well.
万方数据
维普
