{"id":18691079,"url":"https://github.com/nicolasbizzozzero/inpainting","last_synced_at":"2025-04-12T06:18:36.158Z","repository":{"id":144101929,"uuid":"129463613","full_name":"NicolasBizzozzero/Inpainting","owner":"NicolasBizzozzero","description":"Image inpainting via dictionary learning and sparse representation.","archived":false,"fork":false,"pushed_at":"2019-06-05T12:12:59.000Z","size":29696,"stargazers_count":49,"open_issues_count":0,"forks_count":12,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-12T06:18:26.557Z","etag":null,"topics":["dictionary-learning","image-inpainting","inpaint","inpainting","inpainting-methods","lasso","machine-learning","paper-implementations"],"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/NicolasBizzozzero.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":"2018-04-13T23:29:03.000Z","updated_at":"2025-04-03T16:03:39.000Z","dependencies_parsed_at":null,"dependency_job_id":"757aa47e-016e-4d3f-91dc-007049f5560f","html_url":"https://github.com/NicolasBizzozzero/Inpainting","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/NicolasBizzozzero%2FInpainting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NicolasBizzozzero%2FInpainting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NicolasBizzozzero%2FInpainting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NicolasBizzozzero%2FInpainting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NicolasBizzozzero","download_url":"https://codeload.github.com/NicolasBizzozzero/Inpainting/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248525141,"owners_count":21118620,"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":["dictionary-learning","image-inpainting","inpaint","inpainting","inpainting-methods","lasso","machine-learning","paper-implementations"],"created_at":"2024-11-07T10:53:18.961Z","updated_at":"2025-04-12T06:18:36.148Z","avatar_url":"https://github.com/NicolasBizzozzero.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Image inpainting via dictionary learning and sparse representation\nThis project aims at rebuild \"damaged\" pictures by learning a sparse representation of non-damaged patch of the image.\n\n\n## Model\nThe model is composed of 3 Linear regressions (one per channel) with L1 regularization (aka Lasso).\nIt encodes the picture to a HSV color model, normalize its pixels between [-1, 1], and learn which sparse combination of pixels can properly rebuild the picture.\n\n\n## Examples\n\u003ccenter\u003e\n  \u003cimg src=\"https://github.com/NicolasBizzozzero/Inpainting/blob/master/report/res/lena_color_512_0_1.png\" alt=\"Example Lena 10%\"\u003e\n  \u003cimg src=\"https://github.com/NicolasBizzozzero/Inpainting/blob/master/report/res/lena_color_512_0_5.png\" alt=\"Example Lena 50%\"\u003e\n  \u003cimg src=\"https://github.com/NicolasBizzozzero/Inpainting/blob/master/report/res/outdoor_parfait.png\" alt=\"Example outdoor\"\u003e\n\u003c/center\u003e\n\n\n## TODO\n* Implement a CLI.\n* Find a better heuristic for patch approximation order.\n* Rewrite the model in PyTorch for GPU acceleration.\n* Make the linear model a parameter of the Inpainting class.\n\n\n## Sources\n* Bin Shen and Wei Hu and Zhang, Yimin and Zhang, Yu-Jin, Image Inpainting via Sparse Representation Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP ’09)\n* Julien Mairal Sparse coding and Dictionnary Learning for Image Analysis INRIA Visual Recognition and Machine Learning Summer School, 2010\n* A. Criminisi, P. Perez, K. Toyama Region Filling and Object Removal by Exemplar-Based Image Inpainting IEEE Transaction on Image Processing (Vol 13-9), 2004\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnicolasbizzozzero%2Finpainting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnicolasbizzozzero%2Finpainting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnicolasbizzozzero%2Finpainting/lists"}