# Face Super-Resolution Through Wasserstein GANs

arXiv: https://arxiv.org/abs/1705.02438 · HTML: https://mlsanity.com/paper/1705.02438/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2017.

## Built on by (most cited first, 9 of 9)

- [AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis](https://mlsanity.com/paper/2112.12744/) (2021)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [Multimodal-Boost: Multimodal Medical Image Super-Resolution using Multi-Attention Network with Wavelet Transform](https://mlsanity.com/paper/2110.11684/) (2021)
- [SDDPM: Speckle Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2311.10868/) (2023)
- [Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives](https://mlsanity.com/paper/2105.01800/) (2021)
- [3D GANs and Latent Space: A comprehensive survey](https://mlsanity.com/paper/2304.03932/) (2023)
- [Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network](https://mlsanity.com/paper/2211.10532/) (2022)
- [Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss](https://mlsanity.com/paper/2211.10883/) (2022)
- [Potential and challenges of generative adversarial networks for super-resolution in 4D Flow MRI](https://mlsanity.com/paper/2508.14950/) (2025)

## Abstract (arXiv)

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.