2022/10/20 by Bolong Zhang, Juan Chen, Zhang, Bolong +3 · 1 citation
Computer Science · Engineering · Physics and Astronomy · #Advanced Image Processing Techniques #Advanced Optical Sensing Technologies #Algorithm #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Electrical engineering #Engineering #FOS: Computer and information sciences #FOS: Electrical engineering #Geography #High resolution #Image (mathematics) #Image Processing Techniques and Applications #Image and Video Processing (eess.IV) #Image quality #Superresolution #Transformer #Voltage #cs.CV #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2210.11019
published in arXiv (Cornell University) (Cornell University)
arxiv created 2022/10/20 · openalex publication_date 2022/10/20 · arxiv updated 2022/10/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Image super-resolution reconstruction is an important task in the field of image processing technology, which can restore low resolution image to high quality image with high resolution. In recent years, deep learning has been applied in the field of image super-resolution reconstruction. With the continuous development of deep neural network, the quality of the reconstructed images has been greatly improved, but the model complexity has also been increased. In this paper, we propose two lightweight models named as MSwinSR and UGSwinSR based on Swin Transformer. The most important structure in MSwinSR is called Multi-size Swin Transformer Block (MSTB), which mainly contains four parallel multi-head self-attention (MSA) blocks. UGSwinSR combines U-Net and GAN with Swin Transformer. Both of them can reduce the model complexity, but MSwinSR can reach a higher objective quality, while UGSwinSR can reach a higher perceptual quality. The experimental results demonstrate that MSwinSR increases PSNR by 0.07dB compared with the state-of-the-art model SwinIR, while the number of parameters can reduced by 30.68%, and the calculation cost can reduced by 9.936%. UGSwinSR can effectively reduce the amount of calculation of the network, which can reduced by 90.92% compared with SwinIR.