{"id":13488543,"url":"https://github.com/Kaminyou/Dense-Normalization","last_synced_at":"2025-03-28T01:36:15.715Z","repository":{"id":247337598,"uuid":"822726870","full_name":"Kaminyou/Dense-Normalization","owner":"Kaminyou","description":"[ECCV 2024] Official implementation of \"Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization\"","archived":false,"fork":false,"pushed_at":"2024-11-25T08:18:17.000Z","size":25734,"stargazers_count":28,"open_issues_count":1,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-25T09:25:11.913Z","etag":null,"topics":["computer-vision","eccv2024","generative-adversarial-network","generative-model","high-resolution-image","image-to-image-translation","parallelism"],"latest_commit_sha":null,"homepage":"https://kaminyou.com/Dense-Normalization/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kaminyou.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-07-01T17:37:12.000Z","updated_at":"2024-11-25T08:18:21.000Z","dependencies_parsed_at":"2024-10-31T00:41:58.808Z","dependency_job_id":null,"html_url":"https://github.com/Kaminyou/Dense-Normalization","commit_stats":null,"previous_names":["kaminyou/dense-normalization"],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaminyou%2FDense-Normalization","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaminyou%2FDense-Normalization/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaminyou%2FDense-Normalization/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kaminyou%2FDense-Normalization/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kaminyou","download_url":"https://codeload.github.com/Kaminyou/Dense-Normalization/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245952842,"owners_count":20699548,"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":["computer-vision","eccv2024","generative-adversarial-network","generative-model","high-resolution-image","image-to-image-translation","parallelism"],"created_at":"2024-07-31T18:01:17.798Z","updated_at":"2025-03-28T01:36:15.704Z","avatar_url":"https://github.com/Kaminyou.png","language":"Python","funding_links":[],"categories":["I2I translation"],"sub_categories":[],"readme":"[![python](https://img.shields.io/badge/Python-3.9-3776AB.svg?style=flat\u0026logo=python\u0026logoColor=white)](https://www.python.org)\n![version](https://img.shields.io/badge/version-1.0.0-red)\n[![License: AGPL](https://img.shields.io/badge/License-AGPL-yellow.svg)](https://github.com/Kaminyou/Dense-Normalization/blob/main/LICENSE)\n![linting workflow](https://github.com/Kaminyou/Dense-Normalization/actions/workflows/main.yml/badge.svg)\n\u003cdiv align=\"center\"\u003e\n\n\u003ch2\u003eECCV 2024\u003c/h2\u003e\n\u003ch1\u003eEvery Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization\u003c/h1\u003e\n\n[Ming-Yang Ho](https://kaminyou.com/)\u003csup\u003e1\u003c/sup\u003e, \u0026nbsp; [Che-Ming Wu](https://github.com/st9007a)\u003csup\u003e2\u003c/sup\u003e, \u0026nbsp; [Min-Sheng Wu](https://github.com/Min-Sheng)\u003csup\u003e3\u003c/sup\u003e, \u0026nbsp; [Yufeng Jane Tseng](https://www.csie.ntu.edu.tw/en/member/Faculty/Yufeng-Jane-Tseng-95281407)\u003csup\u003e1\u003c/sup\u003e\n\n\u003csup\u003e1\u003c/sup\u003eNational Taiwan University, \u0026nbsp; \u003csup\u003e2\u003c/sup\u003eAmazon Web Services, \u0026nbsp; \u003csup\u003e3\u003c/sup\u003eaetherAI\u003cbr\u003e\n\n[[`Paper (arxiv)`](https://arxiv.org/abs/2407.04245)] [[`Paper (official)`](https://link.springer.com/chapter/10.1007/978-3-031-72995-9_18)] [[`Project Page`](https://kaminyou.com/Dense-Normalization/)]\n\u003cbr\u003e\u003cbr\u003e\u003cimage src=\"./images/teaser.jpg\"/\u003e\n\u003cbr\u003e\u003cimage src=\"./images/framework.jpg\"/\u003e\n\n\u003c/div\u003e\n\n## Get started with an example\nWe provide a simple example (one image from the Kyoto summer2autumn dataset) for you to translate an UHR image with our DN.\n\n### Download example data\n```bash\n$ ./download.sh\n$ unzip simple_example.zip\n```\n\n### Environment preparation\n1. Please check your GPU driver version and modify `Dockerifle` accordingly\n2. Then, execute\n    ```bash\n    $ docker-compose up --build -d\n    ```\n3. Get into the docker container\n    ```bash\n    $ docker exec -it dn-env bash\n    ```\n\n### Inference\n1. In the docker container, please execute\n    ```bash\n    $ python3 transfer.py -c data/japan/config.yaml\n    ```\n2. Then, you can see a translated image at `experiments/japan_CUT/test/IMG_6610/combined_dn_10.png`\n3. To see the image conveniently, you can leverage the provided `visualization.ipynb`. The setup of jupyter notebbok can be achived by\n    - a. modify a port mapping setting in `docker-compose.yml`; e,g, `- 19000:8888`\n    - b. install `jupyter` in the container\n    - c. run your jupyter notebook by `nohup jupyter notebook --ip=0.0.0.0 --port=8888 --allow-root \u0026`\n    - d. open the jupter notebook service on your port (`19000` here)\n\n## Datasets\n### `real2paint` Dataset\nFor the real domain, please download the [UHDM dataset](https://xinyu-andy.github.io/uhdm-page/) from its official website. For the painting domain, we have curated a dataset of high-resolution Vincent van Gogh paintings, which can be downloaded at [link1](https://github.com/Kaminyou/UHR-Vincent-van-Gogh-real2paint) or [link2](https://www.dropbox.com/scl/fi/gohkhvipij61w496eeqdw/vincent_van_gogh.zip?rlkey=vco57kdadendwhy4zzednkk4i\u0026st=d127g9bk\u0026dl=0). Please note that we do not own these images; users should ensure their use does not trigger legal issues.\n\n### `Kyoto-summer2autumn` Dataset\nPlease download it at [link](https://github.com/Kaminyou/Kyoto-summer2autumn).\n\n### `ANHIR` Dataset\nPlease download it at [link](https://anhir.grand-challenge.org/Data/). Please note that we do not own these images; users should ensure their use does not trigger legal issues.\n\n### `ACROBAT` Dataset\nPlease download it at [link](https://acrobat.grand-challenge.org/). Please note that we do not own these images; users should ensure their use does not trigger legal issues.\n\n## Train your model\nThe training of I2I model is the same as [KIN](https://github.com/Kaminyou/URUST). DN is a plugin for any I2I model with InstanceNorm layers.\n\n## Citation\n```\n@InProceedings{10.1007/978-3-031-72995-9_18,\nauthor=\"Ho, Ming-Yang and Wu, Che-Ming and Wu, Min-Sheng and Tseng, Yufeng Jane\",\ntitle=\"Every Pixel Has Its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization\",\nbooktitle=\"Computer Vision -- ECCV 2024\",\nyear=\"2025\",\npublisher=\"Springer Nature Switzerland\",\naddress=\"Cham\",\npages=\"312--328\",\nisbn=\"978-3-031-72995-9\"\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKaminyou%2FDense-Normalization","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FKaminyou%2FDense-Normalization","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FKaminyou%2FDense-Normalization/lists"}