{"id":13723207,"url":"https://github.com/gradslam/gradslam","last_synced_at":"2025-05-16T03:07:08.549Z","repository":{"id":44909750,"uuid":"310478206","full_name":"gradslam/gradslam","owner":"gradslam","description":"gradslam is an open source differentiable dense SLAM library for PyTorch","archived":false,"fork":false,"pushed_at":"2023-09-02T16:35:54.000Z","size":67809,"stargazers_count":1345,"open_issues_count":15,"forks_count":161,"subscribers_count":46,"default_branch":"main","last_synced_at":"2025-04-08T13:14:15.544Z","etag":null,"topics":["3d-reconstruction","deep-learning","machine-learning","robotics","slam"],"latest_commit_sha":null,"homepage":"https://gradslam.github.io/","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/gradslam.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-11-06T03:09:31.000Z","updated_at":"2025-04-06T13:10:34.000Z","dependencies_parsed_at":"2022-08-30T17:12:17.550Z","dependency_job_id":"5c63f7d9-627b-435d-8ab2-e99ea5da8db4","html_url":"https://github.com/gradslam/gradslam","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/gradslam%2Fgradslam","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gradslam%2Fgradslam/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gradslam%2Fgradslam/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/gradslam%2Fgradslam/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/gradslam","download_url":"https://codeload.github.com/gradslam/gradslam/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254459088,"owners_count":22074605,"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","deep-learning","machine-learning","robotics","slam"],"created_at":"2024-08-03T01:01:37.181Z","updated_at":"2025-05-16T03:07:03.533Z","avatar_url":"https://github.com/gradslam.png","language":"Python","funding_links":[],"categories":["Simultaneous Localization and Mapping","Softwares and Libraries"],"sub_categories":["Visual"],"readme":"\n![](assets/gradslam-banner.png)\n\n--------------------------------------------------------------------------------\n\n[![MITLicense](https://img.shields.io/badge/license-MIT-green)](https://opensource.org/licenses/MIT) [![CircleCI](https://circleci.com/gh/gradslam/gradslam.svg?style=shield\u0026circle-token=109c43f395121b987111c85a9cf51d5fd75ea72c)](https://circleci.com/gh/gradslam/gradslam/tree/master) [![Docs](https://readthedocs.org/projects/gradslam/badge/?version=latest)](https://gradslam.readthedocs.io/en/latest/?badge=latest) [![PyPI version](https://badge.fury.io/py/gradslam.svg)](https://badge.fury.io/py/gradslam)\n\n\n\u003cp align=\"center\"\u003e\n\t\u003cimg src=\"assets/pointfusiondemo.gif\" /\u003e\n\u003c/p\u003e\n\n- [Overview](#overview)\n- [Installation](#installation)\n- [Tutorials](https://gradslam.readthedocs.io/en/latest/tutorials.html)\n- [Online Documentation](https://gradslam.readthedocs.io/en/latest/)\n- [Contributing to gradslam](CONTRIBUTING.md)\n\n\n## Overview\ngradslam is a fully differentiable dense SLAM framework. It provides a repository of differentiable building blocks for a dense SLAM system, such as differentiable nonlinear least squares solvers, differentiable ICP (iterative closest point) techniques, differentiable raycasting modules, and differentiable mapping/fusion blocks. One can use these blocks to construct SLAM systems that allow gradients to flow all the way from the outputs of the system (map, trajectory) to the inputs (raw color/depth images, parameters, calibration, etc.).\n\n```python\nrgbdimages = RGBDImages(colors, depths, intrinsics)\nslam = PointFusion()\npointclouds, recovered_poses = slam(rgbdimages)\npointclouds.plotly(0).show()\n```\n\u003cimg src=\"assets/tum-pointfusion.png\" width=\"340\"\u003e\n\n## Installation\n\n### Requirements\n- `pytorch\u003e=1.6.0` (for other pytorch versions see [here](#install-from-local-clone-recommended))\n\n### Using pip (Experimental)\n\n`pip install gradslam`\n\n### Install from GitHub\n\n`pip install 'git+https://github.com/gradslam/gradslam.git'`\n\n### Install from local clone (Recommended)\n```\ngit clone https://github.com/krrish94/chamferdist.git\ncd chamferdist\npip install .\ncd ..\ngit clone https://github.com/gradslam/gradslam.git\ncd gradslam\npip install -e .[dev]\n```\n\n### Verifying the installation\n\nTo verify if `gradslam` has successfully been built, fire up the python interpreter, and import!\n\n```py\nimport gradslam as gs\nprint(gs.__version__)\n```\n\nYou should see the version number displayed.\n\n\n## Citing gradslam\n\nIf you find `gradslam` useful in your work, and are writing up a report/paper about us, we'd appreciate if you cited us. Please use the following bibtex entry.\n\n```\n@inproceedings{gradslam,\n  title={gradSLAM: Dense SLAM meets automatic differentiation},\n  author={{Krishna Murthy}, Jatavallabhula and Saryazdi, Soroush and Iyer, Ganesh and Paull, Liam},\n  booktitle={arXiv},\n  year={2020},\n}\n```\n\n\n## Contributors\n\n* Soroush Saryazdi\n* Krishna Murthy Jatavallabhula\n* Ganesh Iyer\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgradslam%2Fgradslam","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgradslam%2Fgradslam","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgradslam%2Fgradslam/lists"}