{"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/multimodal-unsupervised-image-to-image","title":"Multimodal Unsupervised Image-to-Image Translation","arxiv_id":"1804.04732","date":"2018-04-12","proceeding":"ECCV 2018 9","authors":["Xun Huang","Ming-Yu Liu","Serge Belongie","Jan Kautz"],"abstract":"Unsupervised image-to-image translation is an important and challenging\nproblem in computer vision. Given an image in the source domain, the goal is to\nlearn the conditional distribution of corresponding images in the target\ndomain, without seeing any pairs of corresponding images. While this\nconditional distribution is inherently multimodal, existing approaches make an\noverly simplified assumption, modeling it as a deterministic one-to-one\nmapping. As a result, they fail to generate diverse outputs from a given source\ndomain image. To address this limitation, we propose a Multimodal Unsupervised\nImage-to-image Translation (MUNIT) framework. We assume that the image\nrepresentation can be decomposed into a content code that is domain-invariant,\nand a style code that captures domain-specific properties. To translate an\nimage to another domain, we recombine its content code with a random style code\nsampled from the style space of the target domain. We analyze the proposed\nframework and establish several theoretical results. Extensive experiments with\ncomparisons to the state-of-the-art approaches further demonstrates the\nadvantage of the proposed framework. Moreover, our framework allows users to\ncontrol the style of translation outputs by providing an example style image.\nCode and pretrained models are available at https://github.com/nvlabs/MUNIT","url_abs":"http://arxiv.org/abs/1804.04732v2","url_pdf":"http://arxiv.org/pdf/1804.04732v2.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":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/nvlabs/MUNIT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/AverageName/Cycle_gan_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/AverageName/UI2IT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/Onr/Council-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/arobey1/mbrdl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/eriklindernoren/PyTorch-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/hyperplane-lab/ACL-GAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/taki0112/MUNIT-Tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/yaxingwang/SDIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/yaxingwang/SEMIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://github.com/yaxingwang/UDIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://gitlab.com/nct_tso_public/laparoscopic-image-2-image-translation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-unsupervised-image-to-image","repo_url":"https://gitlab.com/nct_tso_public/surgical-video-sim2real","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":"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-5","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"AFHQ","model":"MUNIT","rank_in_archive_order":2,"of":4,"metrics":{"FID":"41.5"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"Cats-and-Dogs","model":"MUNIT","rank_in_archive_order":1,"of":3,"metrics":{"CIS":"1.039","IS":" 1.050"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-4","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"CelebA-HQ","model":"MUNIT","rank_in_archive_order":2,"of":4,"metrics":{"FID":"31.4"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-1","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"Edge-to-Handbags","model":"MUNIT","rank_in_archive_order":1,"of":4,"metrics":{"Diversity":"0.175","Quality":"50.0%"},"uses_additional_data":false},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-2","task":"Multimodal Unsupervised Image-To-Image Translation","dataset":"Edge-to-Shoes","model":"MUNIT","rank_in_archive_order":1,"of":4,"metrics":{"Diversity":"0.109","Quality":"50.0%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.04732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.04732"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/taki0112/MUNIT-Tensorflow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/arobey1/mbrdl","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaxingwang/UDIT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/nct_tso_public/surgical-video-sim2real","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaxingwang/SDIT","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hyperplane-lab/ACL-GAN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/nct_tso_public/laparoscopic-image-2-image-translation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AverageName/Cycle_gan_pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eriklindernoren/PyTorch-GAN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/AverageName/UI2IT","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Onr/Council-GAN","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nvlabs/MUNIT","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yaxingwang/SEMIT","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"6653be7e9952f17e","entry":"augmentation","repo":"taki0112/MUNIT-Tensorflow","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6653be7e9952f17e"}},{"code_sha256_prefix":"d29bc3068b3eae3f","entry":"flatten","repo":"taki0112/MUNIT-Tensorflow","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/blob/HEAD/ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d29bc3068b3eae3f"}},{"code_sha256_prefix":"813e0e6fd4e0a9c4","entry":"get_loader","repo":"yaxingwang/SDIT","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/yaxingwang/SDIT/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"813e0e6fd4e0a9c4"}},{"code_sha256_prefix":"bb95d212dc8441e6","entry":"load_test_data","repo":"taki0112/MUNIT-Tensorflow","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb95d212dc8441e6"}},{"code_sha256_prefix":"eab7ba887c245523","entry":"preprocessing","repo":"taki0112/MUNIT-Tensorflow","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/taki0112/MUNIT-Tensorflow/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eab7ba887c245523"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}