{"id":20350517,"url":"https://github.com/nuneslu/veigan","last_synced_at":"2025-04-12T01:35:26.034Z","repository":{"id":77350112,"uuid":"196242689","full_name":"nuneslu/VeIGAN","owner":"nuneslu","description":"GAN for Depth Maps object removal","archived":false,"fork":false,"pushed_at":"2019-12-11T02:00:07.000Z","size":65347,"stargazers_count":8,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-25T21:15:35.431Z","etag":null,"topics":["autonomous-vehicles","depth-maps","disparity-images","gans","inpainting"],"latest_commit_sha":null,"homepage":null,"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/nuneslu.png","metadata":{"files":{"readme":"README.md","changelog":null,"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":"2019-07-10T16:48:07.000Z","updated_at":"2023-07-05T09:14:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"b84f7321-1962-46d4-9607-39280c0fc9f8","html_url":"https://github.com/nuneslu/VeIGAN","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/nuneslu%2FVeIGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nuneslu%2FVeIGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nuneslu%2FVeIGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nuneslu%2FVeIGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nuneslu","download_url":"https://codeload.github.com/nuneslu/VeIGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248504668,"owners_count":21115189,"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":["autonomous-vehicles","depth-maps","disparity-images","gans","inpainting"],"created_at":"2024-11-14T22:31:20.391Z","updated_at":"2025-04-12T01:35:26.029Z","avatar_url":"https://github.com/nuneslu.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VeIGAN: Vectorial Inpainting Generative Adversarial Networks for Depth Maps Object Removal\n\n![VeIGAN GIF](https://github.com/nuneslu/VeIGAN/blob/master/examples/IVGif.gif)  \n\nA video of our results can be seen in: https://www.youtube.com/watch?v=0fQ3vPD88-w\n\n## About\nThis code is based on the Generative Inpainting [[1](https://arxiv.org/abs/1801.07892)][[2](https://arxiv.org/abs/1806.03589)] papers and it's [repository](https://github.com/JiahuiYu/generative_inpainting).\n\nBased on the Generative Inpainting network we proposed adaptations to deal with disparity images inpainting. Our results have been publish on [IV 2019](https://ieeexplore.ieee.org/document/8814157) and on this repository we have the code used on this publication.\n\n## Installation\n\nTo use this code, please follow the installation instructions from the original [repository](https://github.com/JiahuiYu/generative_inpainting) since the dependencies are the same.\n\n## Usage\n\nThe directory _/training_data_ has the disparity images for the training and the _/data_flist_ contains the _.flist_ files wich list the images.\n\nFor training the command is:\n```\npython3 train.py\n```\n\nFor testing use:\n```\npython3 test.py --image 'input_image' --mask 'removed_area_mask' --output 'output_image' --checkpoint_dir model_logs/'trained_model_dir'\n```\nFor the paper all the train and test were made in a GeForce GTX 1080ti.\n\n## VeIGAN Examples\n\nDepth map object removal example and the respective 3D mesh reconstruction:\n\nObject Removal from KITTI Images:\n\n![KITTI Disparity Inpainting](https://github.com/nuneslu/VeIGAN/blob/master/examples/example.png)\n\nObject Removal from CityScapes Images:\n\n![CityScapes Disparity Inpainting](https://github.com/nuneslu/VeIGAN/blob/master/examples/spoiler_result.png)\n\n\n## License\n\nCC 4.0 Attribution-NonCommercial International\n\nThe software is for educational and academic research purpose only.\n\n## Citations\n\nPlease cite this work as:\n\n@INPROCEEDINGS{8814157,  \n    author={L. P. N. {Matias} and M. {Sons} and J. R. {Souza} and D. F. {Wolf} and C. {Stiller}},  \n    booktitle={2019 IEEE Intelligent Vehicles Symposium (IV)},  \n    title={VeIGAN: Vectorial Inpainting Generative Adversarial Network for Depth Maps Object Removal},  \n    year={2019},    \n    pages={310-316},  \n    doi={10.1109/IVS.2019.8814157},  \n    ISSN={1931-0587},  \n    month={June},  \n}\n\n@MISC{matias2019environment,  \n    title={Environment reconstruction on depth images using Generative Adversarial Networks},  \n    author={Lucas P. N. Matias and Jefferson R. Souza and Denis F. Wolf},  \n    year={2019},  \n    eprint={1912.03992},  \n    archivePrefix={arXiv},  \n    primaryClass={cs.CV}  \n}\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnuneslu%2Fveigan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnuneslu%2Fveigan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnuneslu%2Fveigan/lists"}