{"id":20885746,"url":"https://github.com/xinshuoweng/aiodrive","last_synced_at":"2025-07-02T17:05:49.758Z","repository":{"id":40958312,"uuid":"255676758","full_name":"xinshuoweng/AIODrive","owner":"xinshuoweng","description":"Official Python/PyTorch Implementation for \"All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds\"","archived":false,"fork":false,"pushed_at":"2023-10-03T22:45:30.000Z","size":72753,"stargazers_count":60,"open_issues_count":11,"forks_count":8,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-05-12T19:39:12.159Z","etag":null,"topics":["challenges","datasets","detection","evaluation","forecasting","perception","point-cloud","tracking"],"latest_commit_sha":null,"homepage":"http://www.aiodrive.org","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xinshuoweng.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}},"created_at":"2020-04-14T17:24:06.000Z","updated_at":"2025-04-08T02:53:01.000Z","dependencies_parsed_at":"2023-09-22T03:21:57.066Z","dependency_job_id":null,"html_url":"https://github.com/xinshuoweng/AIODrive","commit_stats":{"total_commits":54,"total_committers":2,"mean_commits":27.0,"dds":0.01851851851851849,"last_synced_commit":"bcbe6f0ea7ab1aaf3be3975e8efed4e9e39573a6"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/xinshuoweng/AIODrive","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinshuoweng%2FAIODrive","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinshuoweng%2FAIODrive/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinshuoweng%2FAIODrive/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinshuoweng%2FAIODrive/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xinshuoweng","download_url":"https://codeload.github.com/xinshuoweng/AIODrive/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinshuoweng%2FAIODrive/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":263182167,"owners_count":23426630,"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":["challenges","datasets","detection","evaluation","forecasting","perception","point-cloud","tracking"],"created_at":"2024-11-18T08:14:23.378Z","updated_at":"2025-07-02T17:05:49.724Z","avatar_url":"https://github.com/xinshuoweng.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AIODrive\n\n\u003cb\u003eAll-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds\u003c/b\u003e\n\nThis repository contains the official implementation for our manuscript \"[All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with High-Density Long-Range Point Clouds](https://www.xinshuoweng.com/papers/AIODrive/arXiv.pdf)\". Our project website is [here](http://www.aiodrive.org/). If you find our paper or code useful, please cite our paper below:\n\n```\n@article{Weng2020_AIODrive,\nauthor = {Weng, Xinshuo and Man, Yunze and Cheng, Dazhi and Park, Jinhyung and O'Toole, \nMatthew and Kitani, Kris},\njournal = {arXiv},\ntitle = {{All-In-One Drive: A Large-Scale Comprehensive Perception Dataset with \nHigh-Density Long-Range Point Clouds}},\nyear = {2020}\n}\n```\n\n\u003cimg align=\"center\" width=\"98%\" src=\"https://github.com/xinshuoweng/AIODrive/blob/master/demo.gif\"\u003e\n\n## Introduction\nDeveloping datasets that cover comprehensive sensors, annotations and full data distribution is important for innovating robust multi-sensor multi-task perception systems. Though many datasets have been released, they target for different use-cases such as 3D segmentation (SemanticKITTI), radar sensing (nuScenes), large-scale training (Waymo). As a result, we are still in need of a dataset that forms a union of various strengths of existing datasets. To address this challenge, we present the AIODrive dataset, a synthetic large-scale dataset that provides comprehensive sensors, annotations and environmental variations. Specifically, we provide (1) eight sensor modalities (RGB, Stereo, Depth, LiDAR, SPAD-LiDAR, Radar, IMU, GPS), (2) annotations for all mainstream perception tasks (\\emph{e.g.}, detection, tracking, trajectory prediction, segmentation, depth estimation), and (3) rare driving scenarios such as adverse weather and lighting, crowded scenes, high-speed driving, violation of traffic rules, and accidents. In addition to comprehensive data, long-range perception is also important to perception systems as early detection of faraway objects can help prevent collision in high-speed driving scenarios. However, due to the sparsity and limited range of point cloud data in prior datasets, developing and evaluating long-range perception algorithms is challenging. To address the issue, we provide high-density long-range point clouds for LiDAR and SPAD-LiDAR sensors, about 10$\\times$ denser and larger sensing range than Velodyne-64. \n\n## Dependencies:\nThis code depends on my personal toolbox: https://github.com/xinshuoweng/Xinshuo_PyToolbox. Please install the toolbox by\n\n*1. Clone the github repository.*\n~~~shell\ngit clone https://github.com/xinshuoweng/Xinshuo_PyToolbox\n~~~\n\n*2. Install dependency for the toolbox.*\n~~~shell\ncd Xinshuo_PyToolbox\npip install -r requirements.txt\n~~~\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinshuoweng%2Faiodrive","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxinshuoweng%2Faiodrive","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinshuoweng%2Faiodrive/lists"}