Performance Comparison of Deep Learning Models in Image Super-Resolution

In this research, we present a comprehensive comparative analysis of multiple state-of-the-art deep learning models for single image super-resolution (SISR). The models investigated include the Super-Resolution Convolutional Neural Network (SRCNN), Fast Super-Resolution Convolutional Neural Network (FSRCNN), Very Deep Super-Resolution (VDSR) network, Deeply-Recursive Convolutional Network (DRCN), Enhanced Deep Super-Resolution (EDSR) network, Residual Channel Attention Network (RCAN), and Efficient Sub-Pixel Convolutional Neural Network (ESPCN). Each of these models utilizes distinct architectural innovations and optimization techniques to enhance the resolution and quality of low-resolution images. Our study evaluates these models using benchmark datasets, focusing on their performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM).