Bonan Yu1,2, Taiping Mo1,3, Qi Ma1, Qiumei Li1, Peng Sun1,3,*
CMC-Computers, Materials & Continua, Vol.83, No.1, pp. 1057-1078, 2025, DOI:10.32604/cmc.2025.059946
- 26 March 2025
Abstract Super-resolution (SR) reconstruction addresses the challenge of enhancing image resolution, which is critical in domains such as medical imaging, remote sensing, and computational photography. High-quality image reconstruction is essential for enhancing visual details and improving the accuracy of subsequent tasks. Traditional methods, including interpolation techniques and basic CNNs, often fail to recover fine textures and detailed structures, particularly in complex or high-frequency regions. In this paper, we present Deep Supervised Swin Transformer U-Net (DSSTU-Net), a novel architecture designed to improve image SR by integrating Residual Swin Transformer Blocks (RSTB) and Deep Supervision (DS) mechanisms into… More >