{"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/learning-image-to-image-translation-using","title":"Learning image-to-image translation using paired and unpaired training samples","arxiv_id":"1805.03189","date":"2018-05-08","proceeding":null,"authors":["Soumya Tripathy","Juho Kannala","Esa Rahtu"],"abstract":"Image-to-image translation is a general name for a task where an image from\none domain is converted to a corresponding image in another domain, given\nsufficient training data. Traditionally different approaches have been proposed\ndepending on whether aligned image pairs or two sets of (unaligned) examples\nfrom both domains are available for training. While paired training samples\nmight be difficult to obtain, the unpaired setup leads to a highly\nunder-constrained problem and inferior results. In this paper, we propose a new\ngeneral purpose image-to-image translation model that is able to utilize both\npaired and unpaired training data simultaneously. We compare our method with\ntwo strong baselines and obtain both qualitatively and quantitatively improved\nresults. Our model outperforms the baselines also in the case of purely paired\nand unpaired training data. To our knowledge, this is the first work to\nconsider such hybrid setup in image-to-image translation.","url_abs":"http://arxiv.org/abs/1805.03189v1","url_pdf":"http://arxiv.org/pdf/1805.03189v1.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":"learning-image-to-image-translation-using","repo_url":"https://github.com/Blade6570/Learningimage-to-imagetranslationusingpairedandunpairedtrainingsamples","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"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":"https://app.syntology.ai/?focus=1805.03189","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}