{"id":37750058,"url":"https://github.com/uc-vision/smart-tree","last_synced_at":"2026-01-16T14:21:03.233Z","repository":{"id":168073329,"uuid":"637526985","full_name":"uc-vision/smart-tree","owner":"uc-vision","description":"Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization","archived":false,"fork":false,"pushed_at":"2024-05-04T07:05:31.000Z","size":19558,"stargazers_count":20,"open_issues_count":0,"forks_count":0,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-05-05T06:36:16.395Z","etag":null,"topics":["3d","cloud","point","point-clouds","pointcloud","skeleton","skeletonization","sparse-convolution","structure"],"latest_commit_sha":null,"homepage":"","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/uc-vision.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":"2023-05-07T20:27:20.000Z","updated_at":"2024-05-05T06:36:16.396Z","dependencies_parsed_at":null,"dependency_job_id":"abadd7bc-0b9b-44a5-b6a6-f497d2e129d6","html_url":"https://github.com/uc-vision/smart-tree","commit_stats":null,"previous_names":["uc-vision/smart-tree"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/uc-vision/smart-tree","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uc-vision%2Fsmart-tree","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uc-vision%2Fsmart-tree/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uc-vision%2Fsmart-tree/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uc-vision%2Fsmart-tree/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/uc-vision","download_url":"https://codeload.github.com/uc-vision/smart-tree/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/uc-vision%2Fsmart-tree/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28479393,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-16T11:59:17.896Z","status":"ssl_error","status_checked_at":"2026-01-16T11:55:55.838Z","response_time":107,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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","cloud","point","point-clouds","pointcloud","skeleton","skeletonization","sparse-convolution","structure"],"created_at":"2026-01-16T14:21:02.655Z","updated_at":"2026-01-16T14:21:03.226Z","avatar_url":"https://github.com/uc-vision.png","language":"Python","readme":"# \u003ccenter\u003e 💡🧠🤔 Smart-Tree 🌳🌲🌴 \u003c/center\u003e\n\n## 📝 Description:\n\nThis repository contains code from the paper \"Smart-Tree: Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization\". \u003cbr\u003e\nThe code provided is a deep-learning-based skeletonization method for point clouds.\n\n\u003ctable\u003e\n\u003ctr\u003e\n  \u003ctd style=\"text-align: center\"\u003e\u003cimg src=\"images/botanic-pcd.png\", height=100%\u003e\u003c/td\u003e\n  \u003ctd style=\"text-align: center\"\u003e\u003cimg src=\"images/botanic-branch-mesh.png\", height=100%\u003e\u003c/td\u003e\n  \u003ctd style=\"text-align: center\"\u003e\u003cimg src=\"images/botanic-skeleton.png\", height=100%\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n  \u003ctd align=\"center\"\u003eInput point cloud.\u003c/td\u003e\n  \u003ctd align=\"center\"\u003eMesh output.\u003c/td\u003e\n  \u003ctd align=\"center\"\u003eSkeleton output.\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\n\n## 💾 Data:\n\nPlease follow instructions to download data from this \u003ca href=\"https://github.com/uc-vision/synthetic-trees\"\u003elink\u003c/a\u003e. \u003cbr\u003e\n\n## 🔧 Installation:\n\nFirst, make sure you have Conda installed, aswell as \u003ca href=\"https://www.anaconda.com/blog/a-faster-conda-for-a-growing-community\"\u003emamba\u003c/a\u003e.\nThis will ensure the enviroment is created within a resonable timeframe.\n\nTo install smart-tree please use \u003cbr\u003e`bash create-env.sh`\u003cbr\u003e\nThen activate the environment using: \u003cbr\u003e`conda activate smart-tree`\n\n\n## 📈 Training:\n\nTo train the model open smart_tree/conf/training.yaml.\n\nYou will need to update (alternatively these can be overwritten with hydra): \n\n- training.dataset.json_path to the location of where your smart_tree/conf/tree-split.json is stored. \n- training.dataset.directory to the location of where you downloaded the data (you can choose whether to train on the data with foliage or without based on the directory you supply).\n\nYou can experiment with/adjust hyper-parameter settings too.\n\nThe model will then train using the following:\n\n`train-smart-tree`\n\nThe best model weights and model will be stored in the generated outputs directory.\n\n## ▶️ Inference / ☠️ Skeletonization:\n\nWe supply two different models with weights:\n* `noble-elevator-58` contains branch/foliage segmentation. \u003cbr\u003e\n* `peach-forest-65` is only trained on points from the branching structure. \u003cbr\u003e\n\nIf you wish to run smart-tree using your own weights you will need to update the model paths in the `tree-dataset.yaml`. \u003cbr\u003e\n\nTo run smart-tree use: \u003cbr\u003e\n`run-smart-tree +path=cloud_path` \u003cbr\u003e\nwhere `cloud_path` is the path of the point cloud you want to skeletonize. \u003cbr\u003e\nSkeletonization-specific parameters can be adjusted within the `smart_tree/conf/tree-dataset.yaml` config.\n\n## 📜 Citation:\nPlease use the following BibTeX entry to cite our work: \u003cbr\u003e\n\n```\n@inproceedings{dobbs2023smart,\n  title={Smart-Tree: Neural Medial Axis Approximation of Point Clouds for 3D Tree Skeletonization},\n  author={Dobbs, Harry and Batchelor, Oliver and Green, Richard and Atlas, James},\n  booktitle={Iberian Conference on Pattern Recognition and Image Analysis},\n  pages={351--362},\n  year={2023},\n  organization={Springer}\n}\n```\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=uc-vision/smart-tree\u0026type=Date)](https://star-history.com/#uc-vision/smart-tree\u0026Date)\n\n\n## 📥 Contact \n\nShould you have any questions, comments or suggestions please use the following contact details:\nharry.dobbs87@gmail.com\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuc-vision%2Fsmart-tree","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fuc-vision%2Fsmart-tree","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fuc-vision%2Fsmart-tree/lists"}