{"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/in2i-unsupervised-multi-image-to-image","title":"In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks","arxiv_id":"1711.09334","date":"2017-11-26","proceeding":null,"authors":["Pramuditha Perera","Mahdi Abavisani","Vishal M. Patel"],"abstract":"In unsupervised image-to-image translation, the goal is to learn the mapping\nbetween an input image and an output image using a set of unpaired training\nimages. In this paper, we propose an extension of the unsupervised\nimage-to-image translation problem to multiple input setting. Given a set of\npaired images from multiple modalities, a transformation is learned to\ntranslate the input into a specified domain. For this purpose, we introduce a\nGenerative Adversarial Network (GAN) based framework along with a multi-modal\ngenerator structure and a new loss term, latent consistency loss. Through\nvarious experiments we show that leveraging multiple inputs generally improves\nthe visual quality of the translated images. Moreover, we show that the\nproposed method outperforms current state-of-the-art unsupervised\nimage-to-image translation methods.","url_abs":"http://arxiv.org/abs/1711.09334v1","url_pdf":"http://arxiv.org/pdf/1711.09334v1.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":"in2i-unsupervised-multi-image-to-image","repo_url":"https://github.com/PramuPerera/In2I","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"Generative Adversarial Network"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"multimodal-unsupervised-image-to-image","task_name":"Multimodal Unsupervised Image-To-Image Translation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"unsupervised-image-to-image-translation","task_name":"Unsupervised Image-To-Image Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-3","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"EPFL NIR-VIS","model":"In2I","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"23.11"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-image-to-image-translation-on-1","task":"Unsupervised Image-To-Image Translation","dataset":"Freiburg Forest Dataset","model":"In2I","rank_in_archive_order":1,"of":3,"metrics":{"PSNR":"21.65"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.09334","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}