{"id":17296238,"url":"https://github.com/henzler/platonicgan","last_synced_at":"2025-04-14T11:24:07.670Z","repository":{"id":208376927,"uuid":"227869885","full_name":"henzler/platonicgan","owner":"henzler","description":"Escaping Plato’s Cave: 3D Shape from Adversarial Rendering [ICCV 2019]","archived":false,"fork":false,"pushed_at":"2021-06-10T09:24:48.000Z","size":23725,"stargazers_count":44,"open_issues_count":3,"forks_count":11,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-03-28T00:41:38.673Z","etag":null,"topics":["3d-reconstruction","artificial-intelligence","computer-graphics","computer-vision","deeplearning","differentiable-rendering","iccv2019","machine-learning"],"latest_commit_sha":null,"homepage":"https://geometry.cs.ucl.ac.uk/projects/2019/platonicgan/","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/henzler.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}},"created_at":"2019-12-13T15:37:26.000Z","updated_at":"2024-10-03T09:38:47.000Z","dependencies_parsed_at":"2023-11-21T07:59:14.133Z","dependency_job_id":null,"html_url":"https://github.com/henzler/platonicgan","commit_stats":null,"previous_names":["henzler/platonicgan"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/henzler%2Fplatonicgan","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/henzler%2Fplatonicgan/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/henzler%2Fplatonicgan/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/henzler%2Fplatonicgan/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/henzler","download_url":"https://codeload.github.com/henzler/platonicgan/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248869670,"owners_count":21174914,"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":["3d-reconstruction","artificial-intelligence","computer-graphics","computer-vision","deeplearning","differentiable-rendering","iccv2019","machine-learning"],"created_at":"2024-10-15T11:12:18.412Z","updated_at":"2025-04-14T11:24:07.646Z","avatar_url":"https://github.com/henzler.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PlatonicGAN\n\n\nThis repository contains code for the paper [Escaping Plato’s Cave: 3D Shape from Adversarial Rendering](https://geometry.cs.ucl.ac.uk/projects/2019/platonicgan/paper_docs/platonicgan.pdf) (ICCV2019). \n\nMore detailed information and results can be found on our [project page](https://geometry.cs.ucl.ac.uk/projects/2019/platonicgan/).\n\n![Teaser](images/teaser.jpg)\n\n## Data\n\nFor training you can use any image collection you would like. For now two example datasets \"tree\" and \"chanterelle\" are provided under 'datasets/. \nIf you have your own data set go to 'scripts/data' and have a look at the already implemented custom implementations for data sets.\nYou may want to adjust them accordingly or create new ones.\nIn case you want to create a new `Dataset` class you should do so under `scripts/data`.\n\n\n## Usage\n\n### Prerequisites\n\n- Linux (not tested for MacOS or Windows)\n- Python3\n- CPU or NVIDIA GPU\n\n### Installation\n\n\nClone this repo:\n\n```\ngit clone https://github.com/henzler/platonicgan\ncd platonicgan\n```\n\nIn order to install the required python packages run (in a new virtual environment):\n\n```\npip install -r requirements.txt\n```\n\n*Note:* The model was trained with PyTorch 1.0.0, but also tested with Pytorch 1.3.1\n\n### Train\n\nFor training execute the following command (for default config, currently this will train the tree dataset):\n\n`python train.py`\n\nor for a specific config:\n\n`python train.py --config_file=scripts/configs/your_config_file.yaml`\n\n\n### Track training progress\n\nUse tensorboard to visualise intermediate training results:\n\n`tensorboard --logdir=.`\n\n## Bibtex\n\nIf you use this code for your research, please cite our paper.\n\n \n```\n@InProceedings{henzler2019platonicgan,\nauthor = {Henzler, Philipp and Mitra, Niloy J. and Ritschel, Tobias},\ntitle = {Escaping Plato's Cave: 3D Shape From Adversarial Rendering},\nbooktitle = {The IEEE International Conference on Computer Vision (ICCV)},\nmonth = {October},\nyear = {2019}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhenzler%2Fplatonicgan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhenzler%2Fplatonicgan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhenzler%2Fplatonicgan/lists"}