{"id":13934795,"url":"https://github.com/bendangnuksung/Image-OutPainting","last_synced_at":"2025-07-19T19:31:57.573Z","repository":{"id":33035317,"uuid":"141739104","full_name":"bendangnuksung/Image-OutPainting","owner":"bendangnuksung","description":"🏖 Keras Implementation of Painting outside the box","archived":false,"fork":false,"pushed_at":"2022-11-22T04:30:06.000Z","size":495,"stargazers_count":1144,"open_issues_count":12,"forks_count":228,"subscribers_count":43,"default_branch":"master","last_synced_at":"2024-11-21T21:03:05.090Z","etag":null,"topics":["computer-vision","deep-learning","gans","image-outpainting","keras","python","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/bendangnuksung.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}},"created_at":"2018-07-20T17:19:25.000Z","updated_at":"2024-11-12T08:49:48.000Z","dependencies_parsed_at":"2023-01-14T23:15:30.318Z","dependency_job_id":null,"html_url":"https://github.com/bendangnuksung/Image-OutPainting","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/bendangnuksung%2FImage-OutPainting","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bendangnuksung%2FImage-OutPainting/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bendangnuksung%2FImage-OutPainting/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bendangnuksung%2FImage-OutPainting/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bendangnuksung","download_url":"https://codeload.github.com/bendangnuksung/Image-OutPainting/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226666437,"owners_count":17665030,"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","deep-learning","gans","image-outpainting","keras","python","tensorflow"],"created_at":"2024-08-07T23:01:14.395Z","updated_at":"2024-11-27T02:30:48.626Z","avatar_url":"https://github.com/bendangnuksung.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# Keras implementation of Image OutPainting\n\nThis is an implementation of [Painting Outside the Box: Image Outpainting](https://cs230.stanford.edu/projects_spring_2018/posters/8265861.pdf) paper from Standford University. \nSome changes have been made to work with 256*256 image:\n  - Added Identity loss i.e from generated image to the original image\n  - Removed patches from training data. (training pipeline)\n  - Replaced masking with cropping. (training pipeline)\n  - Added convolution layers.\n\n## Results\nThe model was train with [3500 scrapped beach data](https://drive.google.com/open?id=1hKIn-Z8Uf3voESbJZVsapLHESPabjjrb) with agumentation totalling upto 10500 images for 25 epochs.\n![Demo](https://i.imgur.com/ZHtoeDF.jpg)\n\n#### Recursive painting\n![Demo](http://i.imgur.com/pDUpzcY.jpg)\n\n### Install Requirements\n```\nsudo apt-get install curl\nsudo pip3 install -r requirements.txt\n```\n\n## Get Started\n\n1. Prepare Data:\n      ```sh\n      # Downloads the beach data and converts to numpy batch data\n      # saves the Numpy batch data to 'data/prepared_data/'\n      sh prepare_data.sh\n      ```\n2. Build Model\n    * To build Model from scratch you can directly run 'outpaint.ipynb'\n  \u003cbr/\u003eOR\u003cbr/\u003e\n    * You can [Download](https://drive.google.com/open?id=1MfXsRwjx5CTRGBoLx154S0h-Q3rIUNH0) my trained model and move it to 'checkpoint/' and run it.\n\n## References\n* [Painting Outside the Box: Image Outpainting](https://cs230.stanford.edu/projects_spring_2018/posters/8265861.pdf)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbendangnuksung%2FImage-OutPainting","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbendangnuksung%2FImage-OutPainting","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbendangnuksung%2FImage-OutPainting/lists"}