{"id":25638380,"url":"https://github.com/dros1986/filter_removal","last_synced_at":"2025-04-15T00:09:27.900Z","repository":{"id":97889375,"uuid":"94990376","full_name":"dros1986/filter_removal","owner":"dros1986","description":"CNN-based photo-filter removal","archived":false,"fork":false,"pushed_at":"2019-04-01T15:28:53.000Z","size":57792,"stargazers_count":14,"open_issues_count":1,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-15T00:09:08.155Z","etag":null,"topics":["cnn","convolutional-neural-networks","filter-removal","image-enhancement","image-processing","machine-learning","photo-filter","photo-repair","photography","pytorch","unfilering"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dros1986.png","metadata":{"files":{"readme":"readme.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2017-06-21T10:03:21.000Z","updated_at":"2024-08-12T19:10:52.000Z","dependencies_parsed_at":"2023-04-23T05:22:52.026Z","dependency_job_id":null,"html_url":"https://github.com/dros1986/filter_removal","commit_stats":null,"previous_names":[],"tags_count":37,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dros1986%2Ffilter_removal","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dros1986%2Ffilter_removal/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dros1986%2Ffilter_removal/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dros1986%2Ffilter_removal/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dros1986","download_url":"https://codeload.github.com/dros1986/filter_removal/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248981268,"owners_count":21193147,"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":["cnn","convolutional-neural-networks","filter-removal","image-enhancement","image-processing","machine-learning","photo-filter","photo-repair","photography","pytorch","unfilering"],"created_at":"2025-02-23T02:29:37.381Z","updated_at":"2025-04-15T00:09:27.893Z","avatar_url":"https://github.com/dros1986.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![DOI](https://zenodo.org/badge/94990376.svg)](https://zenodo.org/badge/latestdoi/94990376)\n\n\n\nPytorch implementation of the paper:\n\n**Artistic Photo Filter Removal Using CNNs**  \nJournal of Electronic Imaging, SPIE  \n[F. Piccoli](http://www.ivl.disco.unimib.it/people/flavio-piccoli/ \"Flavio Piccoli\"), [C. Cusano](http://www.ivl.disco.unimib.it/people/claudio-cusano/ \"Claudio Cusano\"), [S. Bianco](http://www.ivl.disco.unimib.it/people/simone-bianco/ \"Simone Bianco\"), [R. Schettini](http://www.ivl.disco.unimib.it/people/raimondo-schettini/ \"Raimondo Schettini\")\n\nUsage:\n\n```bash\n# clone this repository\ngit clone --recursive https://github.com/dros1986/filter_removal.git\n# download the dataset\nwget https://drive.google.com/a/campus.unimib.it/uc?export=download\u0026confirm=XAOn\u0026id=1vvLAO__opCjgLfRjAjW3WPWJHNiiVLbs\n# unzip the file\nunzip file.zip -d ./datasets/\n# start training\npython main.py -degin 3 degout 3\n# start test\npython main.py -degin 3 degout 3 --regen ./checkpoint.pth\n```\n\nInput images\n![input](https://github.com/dros1986/filter_removal/blob/master/images/input.png)\n\nOutput images\n![output](https://github.com/dros1986/filter_removal/blob/master/images/output.png)\n\n## Parameters\n| Name | Description | Default |\n| ---- | ----------- | ------- |\n| degin | Degree of the polynomial onto which the color transform will be estimated | 3 |\n| degout | Degree of the polynomial onto which the color transform will be applied | 3 |\n| patchsize | patchsize*patchsize is the number of pixels involved in each color transform | 8 |\n| nrow | Batch size will be nrow*nrow | 5 |\n| indir | Folder containing filtered images | ./datasets/places-instagram/images/ |\n| gtdir | Folder containing original images | ./datasets/places-instagram/images_orig/ |\n| train_list | txt containing train set filenames | ./datasets/places-instagram/train-list.txt |\n| validation_list | txt containing validation set filenames | ./datasets/places-instagram/smallvalidation-list.txt |\n| test_list | txt containing test set filenames | ./datasets/places-instagram/test-list.txt |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdros1986%2Ffilter_removal","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdros1986%2Ffilter_removal","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdros1986%2Ffilter_removal/lists"}