{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/face-super-resolution-through-wasserstein","title":"Face Super-Resolution Through Wasserstein GANs","arxiv_id":"1705.02438","date":"2017-05-06","proceeding":null,"authors":["Zhimin Chen","Yuguang Tong"],"abstract":"Generative adversarial networks (GANs) have received a tremendous amount of\nattention in the past few years, and have inspired applications addressing a\nwide range of problems. Despite its great potential, GANs are difficult to\ntrain. Recently, a series of papers (Arjovsky & Bottou, 2017a; Arjovsky et al.\n2017b; and Gulrajani et al. 2017) proposed using Wasserstein distance as the\ntraining objective and promised easy, stable GAN training across architectures\nwith minimal hyperparameter tuning. In this paper, we compare the performance\nof Wasserstein distance with other training objectives on a variety of GAN\narchitectures in the context of single image super-resolution. Our results\nagree that Wasserstein GAN with gradient penalty (WGAN-GP) provides stable and\nconverging GAN training and that Wasserstein distance is an effective metric to\ngauge training progress.","url_abs":"http://arxiv.org/abs/1705.02438v1","url_pdf":"http://arxiv.org/pdf/1705.02438v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"face-super-resolution-through-wasserstein","repo_url":"https://github.com/MandyZChen/srez","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"face-super-resolution-through-wasserstein","repo_url":"https://github.com/VIGNESHinZONE/Face-Super-Resolution-Through-Wasserstein-GANs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-super-resolution","task_name":"Image Super-Resolution"},{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}