{"id":13936423,"url":"https://github.com/mingyuliutw/UNIT","last_synced_at":"2025-07-19T22:30:32.475Z","repository":{"id":41207682,"uuid":"84034880","full_name":"mingyuliutw/UNIT","owner":"mingyuliutw","description":"Unsupervised Image-to-Image Translation","archived":false,"fork":false,"pushed_at":"2021-09-02T20:38:43.000Z","size":207212,"stargazers_count":1988,"open_issues_count":5,"forks_count":362,"subscribers_count":59,"default_branch":"master","last_synced_at":"2024-11-21T04:44:07.018Z","etag":null,"topics":["deep-learning","gan","image-translation","pix2pix"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mingyuliutw.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2017-03-06T05:47:36.000Z","updated_at":"2024-11-20T14:33:40.000Z","dependencies_parsed_at":"2022-07-21T21:32:56.718Z","dependency_job_id":null,"html_url":"https://github.com/mingyuliutw/UNIT","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mingyuliutw%2FUNIT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mingyuliutw%2FUNIT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mingyuliutw%2FUNIT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mingyuliutw%2FUNIT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mingyuliutw","download_url":"https://codeload.github.com/mingyuliutw/UNIT/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226686717,"owners_count":17666928,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","gan","image-translation","pix2pix"],"created_at":"2024-08-07T23:02:39.617Z","updated_at":"2025-07-19T22:30:32.469Z","avatar_url":"https://github.com/mingyuliutw.png","language":"Python","funding_links":[],"categories":["Python","Paper implementations｜论文实现","Model Deployment library","Paper implementations"],"sub_categories":["Other libraries｜其他库:","PyTorch \u003ca name=\"pytorch\"/\u003e","Other libraries:"],"readme":"[![License CC BY-NC-SA 4.0](https://img.shields.io/badge/license-CC4.0-blue.svg)](https://raw.githubusercontent.com/NVIDIA/FastPhotoStyle/master/LICENSE.md)\n![Python 2.7](https://img.shields.io/badge/python-2.7-green.svg)\n## UNIT: UNsupervised Image-to-image Translation Networks\n\n## New implementation available at imaginaire repository\n\nWe have a reimplementation of the UNIT method that is more performant. It is avaiable at [Imaginaire](https://github.com/NVlabs/imaginaire)\n\n### License\n\nCopyright (C) 2018 NVIDIA Corporation.  All rights reserved.\nLicensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). \n\n### Code usage\n\n-  Please check out our [tutorial](TUTORIAL.md). \n\n-  For multimodal (or many-to-many) image translation, please check out our new work on  [MUNIT](https://github.com/NVlabs/MUNIT).\n\n### What's new.\n\n- 05-02-2018: We now adapt [MUNIT](https://github.com/NVlabs/MUNIT) code structure. For reproducing experiment results in the NIPS paper, please check out [version_02 branch](https://github.com/mingyuliutw/UNIT/tree/version_02).\n\n- 12-21-2017: Release pre-trained synthia-to-cityscape image translation model. See [USAGE.md](TUTORIAL.md) for usage examples.\n\n- 12-14-2017: Added multi-scale discriminators described in the [pix2pixHD](https://arxiv.org/pdf/1711.11585.pdf) paper. To use it simply make the name of the discriminator COCOMsDis.\n\n### Paper\n\n[Ming-Yu Liu, Thomas Breuel, Jan Kautz, \"Unsupervised Image-to-Image Translation Networks\" NIPS 2017 Spotlight, arXiv:1703.00848 2017](https://arxiv.org/abs/1703.00848)\n\n#### Two Minute Paper Summary\n[![](./docs/two-minute-paper.png)](https://youtu.be/dqxqbvyOnMY) (We thank the Two Minute Papers channel for summarizing our work.)\n\n#### The Shared Latent Space Assumption\n[![](./docs/shared-latent-space.png)](https://www.youtube.com/watch?v=nlyXoX2aIek)\n\n#### Result Videos\n\nMore image results are available in the [Google Photo Album](https://photos.app.goo.gl/5x7oIifLh2BVJemb2).\n\n*Left: input.* **Right: neural network generated.** Resolution: 640x480\n\n![](./docs/snowy2summery.gif)\n\n*Left: input.* **Right: neural network generated.** Resolution: 640x480\n\n![](./docs/day2night.gif)\n![](./docs/dog_breed.gif)\n![](./docs/cat_species.gif)\n\n- [Snowy2Summery-01](https://youtu.be/9VC0c3pndbI)\n- [Snowy2Summery-02](https://youtu.be/eUBiiBS1mj0)\n- [Day2Night-01](https://youtu.be/Z_Rxf0TfBJE)\n- [Day2Night-02](https://youtu.be/mmj3iRIQw1k)\n- [Translation Between 5 dog breeds](https://youtu.be/3a6Jc7PabB4)\n- [Translation Between 6 cat species](https://youtu.be/Bwq7BmQ1Vbc)\n\n#### Street Scene Image Translation\nFrom the first row to the fourth row, we show example results on day to night, sunny to rainy, summery to snowy, and real to synthetic image translation (two directions). \n\nFor each image pair, *left is the input image*; **right is the machine generated image.**\n\n![](./docs/street_scene.png)\n\n#### Dog Breed Image Translation\n\n![](./docs/dog_trans.png)\n\n#### Cat Species Image Translation\n\n![](./docs/cat_trans.png)\n\n#### Attribute-based Face Image Translation\n\n![](./docs/faces.png)\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmingyuliutw%2FUNIT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmingyuliutw%2FUNIT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmingyuliutw%2FUNIT/lists"}