{"id":35162107,"url":"https://github.com/v-roman-v/dynfilter3d","last_synced_at":"2026-04-21T20:02:47.494Z","repository":{"id":327983201,"uuid":"1113814741","full_name":"V-Roman-V/DynFilter3D","owner":"V-Roman-V","description":"Dynamic object filtering for 3D LiDAR point clouds using spatiotemporal geometry.","archived":false,"fork":false,"pushed_at":"2025-12-10T14:51:36.000Z","size":4,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-12-10T23:30:31.222Z","etag":null,"topics":["3d-geometry","dynamic-object-detection","dynamic-object-filtering","dynamic-objects","lidar","pcl","point-cloud","python","robotics","tool"],"latest_commit_sha":null,"homepage":"","language":null,"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/V-Roman-V.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-10T13:57:07.000Z","updated_at":"2025-12-10T14:55:37.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/V-Roman-V/DynFilter3D","commit_stats":null,"previous_names":["v-roman-v/dynfilter3d"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/V-Roman-V/DynFilter3D","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V-Roman-V%2FDynFilter3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V-Roman-V%2FDynFilter3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V-Roman-V%2FDynFilter3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V-Roman-V%2FDynFilter3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/V-Roman-V","download_url":"https://codeload.github.com/V-Roman-V/DynFilter3D/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/V-Roman-V%2FDynFilter3D/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32108187,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-21T11:25:29.218Z","status":"ssl_error","status_checked_at":"2026-04-21T11:25:28.499Z","response_time":128,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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-geometry","dynamic-object-detection","dynamic-object-filtering","dynamic-objects","lidar","pcl","point-cloud","python","robotics","tool"],"created_at":"2025-12-28T18:40:10.551Z","updated_at":"2026-04-21T20:02:47.489Z","avatar_url":"https://github.com/V-Roman-V.png","language":null,"readme":"\u003ch1 align=\"center\"\u003eDynFilter3D\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cstrong\u003eDynamic object filtering for 3D LiDAR point clouds using spatiotemporal geometry\u003c/strong\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/status-WIP-yellow.svg\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/python-3.9%20|%203.10%20|%203.11-blue.svg\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/c++-17-blue.svg\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/license-MIT-green.svg\"\u003e\n\u003c/p\u003e\n\n\n\u003e **Status:** Work in progress. The API may change without notice.  \n\u003e **TODO:** Add a teaser image or short demo video illustrating the algorithm.\n\n## Introduction\n\n`dynfilter3d` is a clean, from-scratch Python/C++ toolkit for identifying and filtering dynamic points in LiDAR range data using spatiotemporal information such as surface normals and short-term motion cues.\n\nThe design of this project is inspired by the method described in:\n\n\u003e Falque, R., Le Gentil, C., \u0026 Sukkar, F.  \n\u003e **Dynamic Object Detection in Range Data using Spatiotemporal Normals**.  \n\u003e _Australasian Conference on Robotics and Automation (ACRA), 2023._  \n\u003e https://github.com/UTS-RI/dynamic_object_detection\n\n### Motivation  \n\n- Provide a simple, easy-to-use library/framework for dynamic filtering.  \n- Separate logic from ROS dependency.  \n- Add utilities for visualization, benchmarking, and dataset testing.  \n\n## Features\n\n- Lightweight C++17 core for fast geometric processing.\n- Python bindings via `nanobind`.\n- Dynamic point detection using spatiotemporal normals.\n- High-level Python API for both offline and streaming use.\n- Optional visualization utilities (via `open3d`).\n- Examples on open datasets (e.g. KITTI).\n\n---\n\n## Quick Start (example usage)\n\n```python\nimport numpy as np\nimport dynfilter3d as df\n\n# Load a small sequence of LiDAR scans\nscans = [\n    np.load(\"scan_000.npy\"),\n    np.load(\"scan_001.npy\"),\n    np.load(\"scan_002.npy\"),\n]\n\n# Create detector\nf = df.DynamicFilter3D(window_size=3, min_neighbors=8)\n\n# Estimate temporal surface statistics\nf.fit_sequence(scans)\n\n# Filter dynamic points in the last scan\nmask = f.get_static_points(idx=-1)\nstatic_points = scans[-1][mask]\n\nprint(\"Static points:\", static_points.shape[0])\n```\n\nThe API is still evolving, but this illustrates the intended workflow.\n\n## Installation (from source)\n\n```bash\ngit clone https://github.com/\u003cyour-username\u003e/dynfilter3d.git\ncd dynfilter3d\n\npython -m venv .venv\nsource .venv/bin/activate\n\npip install -U pip\npip install -e .\n```\n\nThis builds the native C++ extension and installs the Python package.\n\n## Command Line Interface (planned)\n\n```bash\ndynfilter3d \\\n    --input \"sequence/*.pcd\" \\\n    --output \"filtered/\" \\\n    --config config/default.yaml\n```\n\n## Datasets\n\nThe package supports LiDAR point clouds in `.pcd`, `.bin`, `.npy`, and custom formats.\nExample scripts will be provided for:\n\n- KITTI odometry,\n- open-source urban LiDAR datasets,\n- synthetic demo point clouds.\n\n---\n\n## License\n\nMIT License — a permissive, open-source license allowing commercial and academic use.\n\n## Acknowledgement\n\nThis project is inspired by the original method:\n\n```\n@inproceedings{falque2023dynamic,\n    title={Dynamic Object Detection in Range data using Spatiotemporal Normals}, \n    author={Raphael Falque and Cedric Le Gentil and Fouad Sukkar},\n    booktitle={Australasian Conference on Robotics and Automation, ACRA},\n    year={2023}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fv-roman-v%2Fdynfilter3d","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fv-roman-v%2Fdynfilter3d","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fv-roman-v%2Fdynfilter3d/lists"}