{"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/usis-unsupervised-semantic-image-synthesis","title":"USIS: Unsupervised Semantic Image Synthesis","arxiv_id":"2109.14715","date":"2021-09-29","proceeding":null,"authors":["George Eskandar","Mohamed Abdelsamad","Karim Armanious","Bin Yang"],"abstract":"Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend on a huge amount of labeled data and cannot be applied in an unpaired setting. On the other hand, generic unpaired image-to-image translation frameworks underperform in comparison, because they color-code semantic layouts and feed them to traditional convolutional networks, which then learn correspondences in appearance instead of semantic content. In this initial work, we propose a new Unsupervised paradigm for Semantic Image Synthesis (USIS) as a first step towards closing the performance gap between paired and unpaired settings. Notably, the framework deploys a SPADE generator that learns to output images with visually separable semantic classes using a self-supervised segmentation loss. Furthermore, in order to match the color and texture distribution of real images without losing high-frequency information, we propose to use whole image wavelet-based discrimination. We test our methodology on 3 challenging datasets and demonstrate its ability to generate multimodal photorealistic images with an improved quality in the unpaired setting.","url_abs":"https://arxiv.org/abs/2109.14715v1","url_pdf":"https://arxiv.org/pdf/2109.14715v1.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":"usis-unsupervised-semantic-image-synthesis","repo_url":"https://github.com/GeorgeEskandar/USIS-Unsupervised-Semantic-Image-Synthesis","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"spade","method_name":"SPADE"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-to-image-translation-on-ade20k-labels","task":"Image-to-Image Translation","dataset":"ADE20K Labels-to-Photos","model":"USIS","rank_in_archive_order":11,"of":16,"metrics":{"FID":"33.2","mIoU":"17.38"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-coco-stuff","task":"Image-to-Image Translation","dataset":"COCO-Stuff Labels-to-Photos","model":"USIS","rank_in_archive_order":11,"of":15,"metrics":{"FID":"27.8","mIoU":"14.06"},"uses_additional_data":false},{"leaderboard":"/sota/image-to-image-translation-on-cityscapes","task":"Image-to-Image Translation","dataset":"Cityscapes Labels-to-Photo","model":"USIS","rank_in_archive_order":13,"of":21,"metrics":{"FID":"53.67","mIoU":"44.78"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}