{"id":20098642,"url":"https://github.com/pfnet/pynif3d","last_synced_at":"2025-10-16T23:57:11.082Z","repository":{"id":47685085,"uuid":"397141414","full_name":"pfnet/pynif3d","owner":"pfnet","description":null,"archived":false,"fork":false,"pushed_at":"2021-08-18T07:26:53.000Z","size":2810,"stargazers_count":97,"open_issues_count":9,"forks_count":4,"subscribers_count":83,"default_branch":"main","last_synced_at":"2025-04-09T09:11:53.994Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pfnet.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-08-17T06:53:45.000Z","updated_at":"2025-02-17T14:39:00.000Z","dependencies_parsed_at":"2022-09-03T08:12:30.523Z","dependency_job_id":null,"html_url":"https://github.com/pfnet/pynif3d","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet%2Fpynif3d","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet%2Fpynif3d/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet%2Fpynif3d/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pfnet%2Fpynif3d/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pfnet","download_url":"https://codeload.github.com/pfnet/pynif3d/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252629340,"owners_count":21779198,"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":[],"created_at":"2024-11-13T17:06:08.511Z","updated_at":"2025-10-16T23:57:10.997Z","avatar_url":"https://github.com/pfnet.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PyNIF3D\n\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://github.com/pfnet/pynif3d/blob/master/LICENSE)\n[![Read the Docs](https://readthedocs.org/projects/pynif3d/badge/?version=latest)](https://pynif3d.readthedocs.io/en/latest/)\n\nPyNIF3D is an open-source PyTorch-based library for research on neural implicit\nfunctions (NIF)-based 3D geometry representation. It aims to accelerate research by \nproviding a modular design that allows for easy extension and combination of NIF-related\ncomponents, as well as readily available paper implementations and dataset loaders.\n\nAs of August 2021, the following implementations are supported:\n\n- [NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (Mildenhall et al., 2020)](https://arxiv.org/abs/2003.08934)\n- [Convolutional Occupancy Networks (Peng et al., 2020)](https://arxiv.org/abs/2003.04618)\n- [Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance (Yariv et al., 2020)](https://arxiv.org/abs/2003.09852)\n\n## Installation\n\nTo get started with PyNIF3D, you can use `pip` to install a copy of this repository on\nyour local machine or build the provided Dockerfile.\n\n### Local Installation\n\n```\npip install --user \"https://github.com/pfnet/pynif3d.git\"\n```\n\nThe following packages need to be installed in order to ensure the proper functioning of\nall the PyNIF3D features:\n\n- torch_scatter\u003e=1.3.0\n- torchsearchsorted\u003e=1.0\n\nA [script](https://github.com/pfnet/pynif3d/blob/main/post_install.bash) has been\nprovided to take care of the installation steps for you. Please download it to a\ndirectory of choice and run:\n\n```\nbash post_install.bash\n```\n\n### Docker Build\n\n#### Enabling CUDA Support\n\nPlease make sure the following dependencies are installed in order to build the Docker \nimage with CUDA support:\n\n- nvidia-docker\n- nvidia-container-runtime\n\nThen register the `nvidia` runtime by adding the following to `/etc/docker/daemon.json`:\n```\n{\n    \"runtimes\": {\n        \"nvidia\": {\n            [...]\n        }\n    },\n    \"default-runtime\": \"nvidia\"\n}\n```\n\nRestart the Docker daemon:\n```\nsudo systemctl restart docker\n```\n\nYou should now be able to build a Docker image with CUDA support.\n\n#### Building Dockerfile\n\n```\ngit clone https://github.com/pfnet/pynif3d.git\ncd pynif3d \u0026\u0026 nvidia-docker build -t pynif3d .\n```\n\n#### Running the Container\n\n```\nnvidia-docker run -it pynif3d bash\n```\n\n\n## Tutorials\n\nGet started with PyNIF3D using the examples provided below:\n\n\u003ctable style=\"text-align: center;\"\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\n        \u003cimg src=\"https://camo.githubusercontent.com/88a39df6c735d3b11571504bcacf9c6a322c743b463e0784fe66d936b8e3f688/68747470733a2f2f70656f706c652e656563732e6265726b656c65792e6564752f7e626d696c642f6e6572662f6c65676f5f3230306b5f323536772e676966\" height=\"150px\" alt=\"\"/\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n        \u003cimg src=\"https://github.com/autonomousvision/convolutional_occupancy_networks/raw/master/media/teaser_matterport.gif\" height=\"150px\" alt=\"\"/\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n        \u003cimg src=\"https://user-images.githubusercontent.com/1044197/123730898-1ca15900-d8d2-11eb-9125-426c8a6f4f82.gif\" height=\"150px\" alt=\"\"/\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\n        \u003ca href=\"https://github.com/pfnet/pynif3d/blob/master/examples/nerf/README.md\"\u003eNeRF Tutorial\u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n        \u003ca href=\"https://github.com/pfnet/pynif3d/blob/master/examples/con/README.md\"\u003eCON Tutorial\u003c/a\u003e\n    \u003c/td\u003e\n    \u003ctd\u003e\n        \u003ca href=\"https://github.com/pfnet/pynif3d/blob/master/examples/idr/README.md\"\u003eIDR Tutorial\u003c/a\u003e\n    \u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\nIn addition to the tutorials, pretrained models are also provided and ready to be used.\nPlease consult [this page](https://github.com/pfnet/pynif3d/blob/master/examples/pretrained_models.md) for more information.\n\n## License\n\nPyNIF3D is released under the MIT license. Please refer to [this document](https://github.com/pfnet/pynif3d/blob/master/LICENSE) for more information.\n\n## Contributing\n\nWe welcome any new contributions to PyNIF3D. Please make sure to read\nthe [contributing guidelines](https://github.com/pfnet/pynif3d/blob/master/CONTRIBUTING.md)\nbefore submitting a pull request.\n\n## Documentation\n\nLearn more about PyNIF3D by reading\nthe [API documentation](http://pynif3d.readthedocs.io/en/latest/).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpfnet%2Fpynif3d","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpfnet%2Fpynif3d","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpfnet%2Fpynif3d/lists"}