Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures

arXiv:2404.06294v1 Announce Type: cross
Abstract: Super-Resolution (SR) is a time-hallowed image processing problem that aims to improve the quality of a Low-Resolution (LR) sample up to the standard of its High-Resolution (HR) counterpart. We aim to address this by introducing Super-Resolution Generator (SuRGe), a fully-convolutional Generative Adversarial Network (GAN)-based architecture for SR. We show that distinct convolutional features obtained at increasing depths of a GAN generator can be optimally combined by a set of learnable convex weights to improve the …

abstract adversarial aim arxiv cs.cv cs.lg divergence eess.iv generative generative adversarial network generative adversarial networks generator image image processing low network networks processing quality resolution sample standard type