{"url":"/task/multimodal-unsupervised-image-to-image","name":"Multimodal Unsupervised Image-To-Image Translation","slug":"multimodal-unsupervised-image-to-image","description_markdown":"Multimodal unsupervised image-to-image translation is the task of producing multiple translations to one domain from a single image in another domain.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [MUNIT: Multimodal UNsupervised Image-to-image Translation](https://github.com/NVlabs/MUNIT) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":17,"papers_with_code":14,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-1","slug":"multimodal-unsupervised-image-to-image-1","dataset":"Edge-to-Handbags","dataset_url":null,"rows_in_archive":4,"metrics":["Diversity","Quality"],"first_row_in_archive_order":{"model":"MUNIT","paper_title":"Multimodal Unsupervised Image-to-Image Translation","paper_url":"/paper/multimodal-unsupervised-image-to-image","paper_date":"2018-04-12","arxiv_id":"1804.04732","code_links":[{"title":"eriklindernoren/PyTorch-GAN","url":"https://github.com/eriklindernoren/PyTorch-GAN"},{"title":"nvlabs/MUNIT","url":"https://github.com/nvlabs/MUNIT"},{"title":"taki0112/MUNIT-Tensorflow","url":"https://github.com/taki0112/MUNIT-Tensorflow"},{"title":"Onr/Council-GAN","url":"https://github.com/Onr/Council-GAN"},{"title":"hyperplane-lab/ACL-GAN","url":"https://github.com/hyperplane-lab/ACL-GAN"},{"title":"yaxingwang/SEMIT","url":"https://github.com/yaxingwang/SEMIT"},{"title":"yaxingwang/SDIT","url":"https://github.com/yaxingwang/SDIT"},{"title":"arobey1/mbrdl","url":"https://github.com/arobey1/mbrdl"},{"title":"AverageName/UI2IT","url":"https://github.com/AverageName/UI2IT"},{"title":"AverageName/Cycle_gan_pytorch","url":"https://github.com/AverageName/Cycle_gan_pytorch"},{"title":"nct_tso_public/laparoscopic-image-2-image-translation","url":"https://gitlab.com/nct_tso_public/laparoscopic-image-2-image-translation"},{"title":"nct_tso_public/surgical-video-sim2real","url":"https://gitlab.com/nct_tso_public/surgical-video-sim2real"},{"title":"yaxingwang/UDIT","url":"https://github.com/yaxingwang/UDIT"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-2","slug":"multimodal-unsupervised-image-to-image-2","dataset":"Edge-to-Shoes","dataset_url":null,"rows_in_archive":4,"metrics":["Diversity","Quality"],"first_row_in_archive_order":{"model":"MUNIT","paper_title":"Multimodal Unsupervised Image-to-Image Translation","paper_url":"/paper/multimodal-unsupervised-image-to-image","paper_date":"2018-04-12","arxiv_id":"1804.04732","code_links":[{"title":"eriklindernoren/PyTorch-GAN","url":"https://github.com/eriklindernoren/PyTorch-GAN"},{"title":"nvlabs/MUNIT","url":"https://github.com/nvlabs/MUNIT"},{"title":"taki0112/MUNIT-Tensorflow","url":"https://github.com/taki0112/MUNIT-Tensorflow"},{"title":"Onr/Council-GAN","url":"https://github.com/Onr/Council-GAN"},{"title":"hyperplane-lab/ACL-GAN","url":"https://github.com/hyperplane-lab/ACL-GAN"},{"title":"yaxingwang/SEMIT","url":"https://github.com/yaxingwang/SEMIT"},{"title":"yaxingwang/SDIT","url":"https://github.com/yaxingwang/SDIT"},{"title":"arobey1/mbrdl","url":"https://github.com/arobey1/mbrdl"},{"title":"AverageName/UI2IT","url":"https://github.com/AverageName/UI2IT"},{"title":"AverageName/Cycle_gan_pytorch","url":"https://github.com/AverageName/Cycle_gan_pytorch"},{"title":"nct_tso_public/laparoscopic-image-2-image-translation","url":"https://gitlab.com/nct_tso_public/laparoscopic-image-2-image-translation"},{"title":"nct_tso_public/surgical-video-sim2real","url":"https://gitlab.com/nct_tso_public/surgical-video-sim2real"},{"title":"yaxingwang/UDIT","url":"https://github.com/yaxingwang/UDIT"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-4","slug":"multimodal-unsupervised-image-to-image-4","dataset":"CelebA-HQ","dataset_url":"/dataset/celeba-hq","rows_in_archive":4,"metrics":["FID"],"first_row_in_archive_order":{"model":"StarGAN v2","paper_title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","paper_url":"/paper/stargan-v2-diverse-image-synthesis-for","paper_date":"2019-12-04","arxiv_id":"1912.01865","code_links":[{"title":"clovaai/stargan-v2","url":"https://github.com/clovaai/stargan-v2"},{"title":"naver-ai/StyleMapGAN","url":"https://github.com/naver-ai/StyleMapGAN"},{"title":"mindslab-ai/hififace","url":"https://github.com/mindslab-ai/hififace"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"taki0112/StarGAN_v2-Tensorflow","url":"https://github.com/taki0112/StarGAN_v2-Tensorflow"},{"title":"eps696/stargan2","url":"https://github.com/eps696/stargan2"},{"title":"KbeautyHair/BaselineModel","url":"https://github.com/KbeautyHair/BaselineModel"},{"title":"karlchahine/neural-cover-selection-for-image-steganography","url":"https://github.com/karlchahine/neural-cover-selection-for-image-steganography"},{"title":"UdonDa/StarGAN-v2-pytorch-nonofficial","url":"https://github.com/UdonDa/StarGAN-v2-pytorch-nonofficial"},{"title":"SUPERSHOPxyz/stylegan3-gradient","url":"https://github.com/SUPERSHOPxyz/stylegan3-gradient"},{"title":"threeracha/Chuibbo-Flask-Server","url":"https://github.com/threeracha/Chuibbo-Flask-Server"},{"title":"zzz2010/starganv2_paddle","url":"https://github.com/zzz2010/starganv2_paddle"},{"title":"2023-MindSpore-4/Code7","url":"https://github.com/2023-MindSpore-4/Code7/tree/main/StarGAN"},{"title":"sss20young/Chuibbo-Flask-Server","url":"https://github.com/sss20young/Chuibbo-Flask-Server"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-5","slug":"multimodal-unsupervised-image-to-image-5","dataset":"AFHQ","dataset_url":"/dataset/afhq","rows_in_archive":4,"metrics":["FID"],"first_row_in_archive_order":{"model":"StarGAN v2","paper_title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","paper_url":"/paper/stargan-v2-diverse-image-synthesis-for","paper_date":"2019-12-04","arxiv_id":"1912.01865","code_links":[{"title":"clovaai/stargan-v2","url":"https://github.com/clovaai/stargan-v2"},{"title":"naver-ai/StyleMapGAN","url":"https://github.com/naver-ai/StyleMapGAN"},{"title":"mindslab-ai/hififace","url":"https://github.com/mindslab-ai/hififace"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"taki0112/StarGAN_v2-Tensorflow","url":"https://github.com/taki0112/StarGAN_v2-Tensorflow"},{"title":"eps696/stargan2","url":"https://github.com/eps696/stargan2"},{"title":"KbeautyHair/BaselineModel","url":"https://github.com/KbeautyHair/BaselineModel"},{"title":"karlchahine/neural-cover-selection-for-image-steganography","url":"https://github.com/karlchahine/neural-cover-selection-for-image-steganography"},{"title":"UdonDa/StarGAN-v2-pytorch-nonofficial","url":"https://github.com/UdonDa/StarGAN-v2-pytorch-nonofficial"},{"title":"SUPERSHOPxyz/stylegan3-gradient","url":"https://github.com/SUPERSHOPxyz/stylegan3-gradient"},{"title":"threeracha/Chuibbo-Flask-Server","url":"https://github.com/threeracha/Chuibbo-Flask-Server"},{"title":"zzz2010/starganv2_paddle","url":"https://github.com/zzz2010/starganv2_paddle"},{"title":"2023-MindSpore-4/Code7","url":"https://github.com/2023-MindSpore-4/Code7/tree/main/StarGAN"},{"title":"sss20young/Chuibbo-Flask-Server","url":"https://github.com/sss20young/Chuibbo-Flask-Server"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image","slug":"multimodal-unsupervised-image-to-image","dataset":"Cats-and-Dogs","dataset_url":"/dataset/cats","rows_in_archive":3,"metrics":["CIS","IS"],"first_row_in_archive_order":{"model":"MUNIT","paper_title":"Multimodal Unsupervised Image-to-Image Translation","paper_url":"/paper/multimodal-unsupervised-image-to-image","paper_date":"2018-04-12","arxiv_id":"1804.04732","code_links":[{"title":"eriklindernoren/PyTorch-GAN","url":"https://github.com/eriklindernoren/PyTorch-GAN"},{"title":"nvlabs/MUNIT","url":"https://github.com/nvlabs/MUNIT"},{"title":"taki0112/MUNIT-Tensorflow","url":"https://github.com/taki0112/MUNIT-Tensorflow"},{"title":"Onr/Council-GAN","url":"https://github.com/Onr/Council-GAN"},{"title":"hyperplane-lab/ACL-GAN","url":"https://github.com/hyperplane-lab/ACL-GAN"},{"title":"yaxingwang/SEMIT","url":"https://github.com/yaxingwang/SEMIT"},{"title":"yaxingwang/SDIT","url":"https://github.com/yaxingwang/SDIT"},{"title":"arobey1/mbrdl","url":"https://github.com/arobey1/mbrdl"},{"title":"AverageName/UI2IT","url":"https://github.com/AverageName/UI2IT"},{"title":"AverageName/Cycle_gan_pytorch","url":"https://github.com/AverageName/Cycle_gan_pytorch"},{"title":"nct_tso_public/laparoscopic-image-2-image-translation","url":"https://gitlab.com/nct_tso_public/laparoscopic-image-2-image-translation"},{"title":"nct_tso_public/surgical-video-sim2real","url":"https://gitlab.com/nct_tso_public/surgical-video-sim2real"},{"title":"yaxingwang/UDIT","url":"https://github.com/yaxingwang/UDIT"}],"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}},{"leaderboard":"/sota/multimodal-unsupervised-image-to-image-3","slug":"multimodal-unsupervised-image-to-image-3","dataset":"EPFL NIR-VIS","dataset_url":null,"rows_in_archive":3,"metrics":["PSNR"],"first_row_in_archive_order":{"model":"In2I","paper_title":"In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks","paper_url":"/paper/in2i-unsupervised-multi-image-to-image","paper_date":"2017-11-26","arxiv_id":"1711.09334","code_links":[{"title":"PramuPerera/In2I","url":"https://github.com/PramuPerera/In2I"}],"syntology":null}}],"datasets":[{"url":"/dataset/celeba-hq","name":"CelebA-HQ","full_name":"CelebA-HQ","num_papers_in_archive":954},{"url":"/dataset/afhq","name":"AFHQ","full_name":"Animal Faces-HQ","num_papers_in_archive":327},{"url":"/dataset/cats","name":"CATS","full_name":"Color and Thermal Stereo Benchmark","num_papers_in_archive":11},{"url":"/dataset/ffhq-aging","name":"FFHQ-Aging","full_name":null,"num_papers_in_archive":6}],"subtasks":[],"parent_tasks":[{"url":"/task/image-to-image-translation","name":"Image-to-Image Translation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":14,"of":14,"tagged_in_all":17,"items":[{"url":"/paper/unpaired-image-to-image-translation-using","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","date":"2017-03-30","arxiv_id":"1703.10593","repositories_listed":190,"syntology":{"n":31,"n_ran":6,"n_unverified":25,"n_pointer_only":6}},{"url":"/paper/stargan-v2-diverse-image-synthesis-for","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","date":"2019-12-04","arxiv_id":"1912.01865","repositories_listed":14,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/multimodal-unsupervised-image-to-image","title":"Multimodal Unsupervised Image-to-Image Translation","date":"2018-04-12","arxiv_id":"1804.04732","repositories_listed":13,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/unsupervised-image-to-image-translation","title":"Unsupervised Image-to-Image Translation Networks","date":"2017-03-02","arxiv_id":"1703.00848","repositories_listed":8,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":1}},{"url":"/paper/diverse-image-to-image-translation-via","title":"Diverse Image-to-Image Translation via Disentangled Representations","date":"2018-08-02","arxiv_id":"1808.00948","repositories_listed":7,"syntology":null},{"url":"/paper/lifespan-age-transformation-synthesis","title":"Lifespan Age Transformation Synthesis","date":"2020-03-21","arxiv_id":"2003.09764","repositories_listed":2,"syntology":null},{"url":"/paper/mode-seeking-generative-adversarial-networks","title":"Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis","date":"2019-03-13","arxiv_id":"1903.05628","repositories_listed":2,"syntology":null},{"url":"/paper/wavelet-based-unsupervised-label-to-image-1","title":"Wavelet-based Unsupervised Label-to-Image Translation","date":"2023-05-16","arxiv_id":"2305.09647","repositories_listed":1,"syntology":null},{"url":"/paper/a-style-aware-discriminator-for-controllable","title":"A Style-aware Discriminator for Controllable Image Translation","date":"2022-03-29","arxiv_id":"2203.15375","repositories_listed":1,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/image-to-image-translation-via-hierarchical","title":"Image-to-image Translation via Hierarchical Style Disentanglement","date":"2021-03-02","arxiv_id":"2103.01456","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-cycle-colleagues-are-all-you-1","title":"Breaking the Cycle - Colleagues Are All You Need","date":"2020-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/high-resolution-daytime-translation-without","title":"High-Resolution Daytime Translation Without Domain Labels","date":"2020-03-19","arxiv_id":"2003.08791","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-cycle-colleagues-are-all-you","title":"Breaking the cycle -- Colleagues are all you need","date":"2019-11-24","arxiv_id":"1911.10538","repositories_listed":1,"syntology":null},{"url":"/paper/in2i-unsupervised-multi-image-to-image","title":"In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks","date":"2017-11-26","arxiv_id":"1711.09334","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}