Face Super-Resolution Through Wasserstein GANs

Abstract

Generative adversarial networks (GANs) have received a tremendous amount of attention in the past few years, and have inspired applications addressing a wide range of problems. Despite its great potential, GANs are difficult to train. Recently, a series of papers (Arjovsky & Bottou, 2017a; Arjovsky et al. 2017b; and Gulrajani et al. 2017) proposed using Wasserstein distance as the training objective and promised easy, stable GAN training across architectures with minimal hyperparameter tuning. In this paper, we compare the performance of Wasserstein distance with other training objectives on a variety of GAN architectures in the context of single image super-resolution. Our results agree that Wasserstein GAN with gradient penalty (WGAN-GP) provides stable and converging GAN training and that Wasserstein distance is an effective metric to gauge training progress.

References in corpus (4)

• Generative Adversarial Text to Image Synthesis
• NIPS 2016 Tutorial: Generative Adversarial Networks
• A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models
• On distinguishability criteria for estimating generative models

Cited by in corpus (8)

• On Low-Resolution Face Recognition in the Wild: Comparisons and New Techniques
• Face Recognition in Low Quality Images: A Survey
• Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives
• Deep Learning-based Face Super-Resolution: A Survey
• Artist Style Transfer Via Quadratic Potential
• Generative Adversarial Network with Multi-Branch Discriminator for Cross-Species Image-to-Image Translation
• HypervolGAN: An efficient approach for GAN with multi-objective training function
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image