{"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/composable-unpaired-image-to-image","title":"Composable Unpaired Image to Image Translation","arxiv_id":"1804.05470","date":"2018-04-16","proceeding":null,"authors":["Laura Graesser","Anant Gupta"],"abstract":"There has been remarkable recent work in unpaired image-to-image translation.\nHowever, they're restricted to translation on single pairs of distributions,\nwith some exceptions. In this study, we extend one of these works to a scalable\nmultidistribution translation mechanism. Our translation models not only\nconverts from one distribution to another but can be stacked to create\ncomposite translation functions. We show that this composite property makes it\npossible to generate images with characteristics not seen in the training set.\nWe also propose a decoupled training mechanism to train multiple distributions\nseparately, which we show, generates better samples than isolated joint\ntraining. Further, we do a qualitative and quantitative analysis to assess the\nplausibility of the samples. The code is made available at\nhttps://github.com/lgraesser/im2im2im.","url_abs":"http://arxiv.org/abs/1804.05470v1","url_pdf":"http://arxiv.org/pdf/1804.05470v1.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":"composable-unpaired-image-to-image","repo_url":"https://github.com/lgraesser/im2im2im","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}