Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures
This work addresses the problem of improving image quality for applications like photography and medical imaging, but it is incremental as it builds on existing GAN frameworks.
The authors tackled image super-resolution by introducing SuRGe, a fully-convolutional GAN-based architecture that optimally combines convolutional features and uses divergence losses, achieving superior performance compared to 18 state-of-the-art methods on 10 benchmark datasets.
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 quality of generated SR samples. In the process, we employ the Jensen-Shannon and the Gromov-Wasserstein losses respectively between the SR-HR and LR-SR pairs of distributions to further aid the generator of SuRGe to better exploit the available information in an attempt to improve SR. Moreover, we train the discriminator of SuRGe with the Wasserstein loss with gradient penalty, to primarily prevent mode collapse. The proposed SuRGe, as an end-to-end GAN workflow tailor-made for super-resolution, offers improved performance while maintaining low inference time. The efficacy of SuRGe is substantiated by its superior performance compared to 18 state-of-the-art contenders on 10 benchmark datasets.