ESR-DDLN : Enhanced Single Image Super-Resolution Via Dual-Domain Learning Network

Most existing CNN-based super-resolution (SR) methods focus solely on the spatial domain. We argue that frequency domain details are essential for reconstructing fine textures and patterns. To leverage the frequency information, this paper presents a novel Dual-Domain Learning Network (DDLN) for enhanced image SR. Specifically, DDLN includes Deep Dual-Domain Learning Blocks (DDLB), a Cross Modal Distillation Loss and a pioneering Discriminator. First, DDLB can capture comprehensive image details via simultaneous feature optimization in spatial and frequency domains. Next, the Cross Modal Distillation Loss guides the fusion of spatial and frequency features, enhancing the network’s learning capability. Finally, the pioneering Discriminator with full complex-valued convolution processes images converted from HSV to complex form, boosting SR image quality and realism. Comparative experiments on standard datasets demonstrate significant improvements over current techniques, showcasing the potential of dual-domain approaches in SR and offering novel insights for future research.

I. Introduction

In the digital era, image super-resolution (SR) has emerged as a critical discipline within the domain of computer vision, focusing on reconstructing high-resolution (HR) images from their low-resolution (LR) counterparts. The pursuit of image SR is to enhance image quality and details, which is crucial for various applications, including medical imaging, satellite imaging, and surveillance systems.