{"id":20731465,"url":"https://github.com/opendrivelab/openlane-v2","last_synced_at":"2025-05-16T02:07:23.751Z","repository":{"id":89200998,"uuid":"560272969","full_name":"OpenDriveLab/OpenLane-V2","owner":"OpenDriveLab","description":"[NeurIPS 2023 Track Datasets and Benchmarks] OpenLane-V2: The First Perception and Reasoning Benchmark for Road Driving","archived":false,"fork":false,"pushed_at":"2024-09-18T02:35:14.000Z","size":10437,"stargazers_count":590,"open_issues_count":10,"forks_count":67,"subscribers_count":22,"default_branch":"master","last_synced_at":"2025-05-12T01:13:17.845Z","etag":null,"topics":["3d-lane-detection","topology-reasoning","traffic-element-recognition"],"latest_commit_sha":null,"homepage":"https://proceedings.neurips.cc/paper_files/paper/2023/hash/3c0a4c8c236144f1b99b7e1531debe9c-Abstract-Datasets_and_Benchmarks.html","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OpenDriveLab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT","threat_model":null,"audit":null,"citation":"CITATION","codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"github":["OpenDriveLab"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":null}},"created_at":"2022-11-01T05:24:06.000Z","updated_at":"2025-05-11T10:04:32.000Z","dependencies_parsed_at":"2024-01-05T07:38:20.484Z","dependency_job_id":"b7df3ff7-3972-436b-aded-ca61ef51eb32","html_url":"https://github.com/OpenDriveLab/OpenLane-V2","commit_stats":{"total_commits":108,"total_committers":12,"mean_commits":9.0,"dds":0.4444444444444444,"last_synced_commit":"f085b3dad6bf12e88282e990cbc3704cff226821"},"previous_names":[],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FOpenLane-V2","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FOpenLane-V2/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FOpenLane-V2/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FOpenLane-V2/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OpenDriveLab","download_url":"https://codeload.github.com/OpenDriveLab/OpenLane-V2/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254453652,"owners_count":22073617,"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-lane-detection","topology-reasoning","traffic-element-recognition"],"created_at":"2024-11-17T05:14:57.447Z","updated_at":"2025-05-16T02:07:23.724Z","avatar_url":"https://github.com/OpenDriveLab.png","language":"Jupyter Notebook","funding_links":["https://github.com/sponsors/OpenDriveLab"],"categories":[],"sub_categories":[],"readme":"\u003cdiv id=\"top\" align=\"center\"\u003e\n\n# OpenLane-V2\n**The World's First Perception and Reasoning Benchmark for Scene Structure in Autonomous Driving.**\n\n[![OpenLane-V2](https://img.shields.io/badge/OpenLane--V2-v2.0-blueviolet)](/data)\n[![devkit](https://img.shields.io/badge/devkit-v2.1.0-blueviolet)](/docs/getting_started.md)\n[![LICENSE](https://img.shields.io/badge/license-Apache%202.0-blue)](#license--citation)\n[![testserver](https://img.shields.io/badge/Test%20Server-%F0%9F%A4%97-ffc107)](https://huggingface.co/spaces/AGC2024/mapless-driving-2024)\n\n\u003c!-- **English | [中文](./README-zh-hans.md)**\n\n_In terms of ambiguity, the English version shall prevail._ --\u003e\n\n\u003c/div\u003e\n\n\u003e - [Paper](https://proceedings.neurips.cc/paper_files/paper/2023/hash/3c0a4c8c236144f1b99b7e1531debe9c-Abstract-Datasets_and_Benchmarks.html) (Accepted at NeurIPS 2023 Track Datasets and Benchmarks)\n\u003e - [CVPR 2023 Autonomous Driving Challenge - OpenLane Topology Track](https://opendrivelab.com/challenge2023/#openlane_topology)\n\u003e - [CVPR 2024 Autonomous Grand Challenge - Mapless Driving Track](https://opendrivelab.com/challenge2024/#mapless_driving)\n\u003e - Point of contact: [Huijie (王晖杰)](mailto:wanghuijie@pjlab.org.cn) or [Tianyu (李天羽)](mailto:litianyu@pjlab.org.cn)\n\n## Leaderboard\n\n### Mapless Driving at CVPR 2024 AGC (Server remains `active`)\nWe maintain a [leaderboard](https://opendrivelab.com/challenge2024/#mapless_driving) and [test server](https://huggingface.co/spaces/AGC2024/mapless-driving-2024) on the task of **Driving Scene Topology**. If you wish to add new / modify results to the leaderboard, please drop us an email.\n\n- [Challenge 2024](https://opendrivelab.com/challenge2024/#mapless_driving)\n\n![image](https://github.com/user-attachments/assets/2ef60d09-c875-4891-abbc-c2400ab0a283)\n\n\n### OpenLane Topology Challenge at CVPR 2023 (Server remains `active`)\nWe maintain a [leaderboard](https://opendrivelab.com/challenge2023/#openlane_topology) and [test server](https://eval.ai/web/challenges/challenge-page/1925/overview) on the task of **OpenLane Topology**. If you wish to add new / modify results to the leaderboard, please drop us an email following the instructions [here](https://eval.ai/web/challenges/challenge-page/1925/submission).\n\n- [Challenge 2023](https://opendrivelab.com/challenge2023/#openlane_topology)\n\n![image](https://github.com/OpenDriveLab/OpenLane-V2/assets/29263416/4c1d7dc5-ce00-40de-8907-71060b6ca2f9)\n\n\n## Table of Contents\n- [News](#news)\n- [Introducing `OpenLane-V2 Update`](#introducing-openlane-v2-update)\n- [Task and Evaluation](#task-and-evaluation)\n- [Highlights](#highlights-of-openlane-v2)\n- [Getting Started](#getting-started)\n- [License \u0026 Citation](#license--citation)\n- [Related Resources](#related-resources)\n\n\n## News\n\n\u003e Note\n\u003e \n\u003e The difference between `v1.x` and `v2.x` is that we updated APIs and materials on lane segment and SD map in `v2.x`.\n\u003e\n\u003e ❗️Update on **evaluation metrics** led to differences in TOP scores between `vx.1` ([`v1.1`](https://github.com/OpenDriveLab/OpenLane-V2/releases/tag/v1.1.0), [`v2.1`](https://github.com/OpenDriveLab/OpenLane-V2/releases/tag/v2.1.0)) and `vx.0` (`v1.0`, `v2.0`).\n\u003e We encourage the use of **`vx.1`** metrics.\n\u003e For more details please see issue [#76](https://github.com/OpenDriveLab/OpenLane-V2/issues/76).\n\n- **`2024/06/01`** The [Autonomous Grand Challenge](https://opendrivelab.com/challenge2024/#mapless_driving) wraps up.\n- **`2024/03/01`** We are hosting **CVPR 2024 Autonomous Grand Challenge**.\n- **`2023/11/01`** Devkit `v2.1.0` and `v1.1.0` released.\n- **`2023/08/28`** Dataset `subset_B` released.\n- **`2023/07/21`** Dataset `v2.0` and Devkit `v2.0.0` released.\n- **`2023/07/05`** The [test server of OpenLane Topology](https://eval.ai/web/challenges/challenge-page/1925/overview) is re-opened.\n- **`2023/06/01`** The [Challenge at the CVPR 2023 Workshop](https://opendrivelab.com/challenge2023/#openlane_topology) wraps up.\n- **`2023/04/21`** A baseline based on [InternImage](https://github.com/OpenGVLab/InternImage) released. Check out [here](https://github.com/OpenGVLab/InternImage/tree/master/autonomous_driving/openlane-v2).\n- **`2023/04/20`** [OpenLane-V2 paper](https://arxiv.org/abs/2304.10440) is available on arXiv.\n- **`2023/02/15`** Dataset `v1.0`, Devkit `v1.0.0`, and baseline model released.\n- **`2023/01/15`** Initial OpenLane-V2 dataset sample `v0.1` released.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Introducing `OpenLane-V2 Update`\n\nWe are happy to announce an important update to the OpenLane family, featuring two sets of additional data and annotations.\n\n- **`Map Element Bucket`.** We provide a diverse span of road elements (as a `bucket`) to build the driving scene - on par with all elements in HD Map. Armed with the newly introduced [**lane segment**](/docs/features.md#map-element-bucket) representations, we unify various map elements to incorporate comprehensive aspects of the captured static scenes to empower [DriveAGI](https://github.com/OpenDriveLab/DriveAGI).  \n:bell: The proposed **lane segment** representation is published with [**LaneSegNet**](https://github.com/OpenDriveLab/LaneSegNet) in ICLR 2024!\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/OpenDriveLab/OpenLane-V2/assets/29263416/77846f69-fe77-45aa-b769-e85fd98a0596\" width=\"696px\"\u003e\n\u003c/p\u003e\n\n-  **`Standard-definition (SD) Map`.** As a new sensor input, [**SD Map**](/docs/features.md#sd-map) supplements multi-view images with topological and positional priors to strengthen structural acknowledge in the neural networks.\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://github.com/OpenDriveLab/OpenLane-V2/assets/29263416/0b3f4678-fa57-4187-afd6-e55db12a76a6\" width=\"696px\"\u003e\n\u003c/p\u003e\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Task and Evaluation\n\n### Driving Scene Topology\n\nGiven sensor inputs, lane segments are required to be perceived, instead of lane centerlines in the task of OpenLane Topology.\nBesides, pedestrian crossings and road boundaries are also desired to build a comprehensive understanding of the driving scenes.\nThe [OpenLane-V2 UniScore (OLUS)](docs/metrics.md#driving-scene-topology) is utilized  to summarize model performance in all aspects.\n\n### OpenLane Topology\nGiven sensor inputs, participants are required to deliver not only perception results of lanes and traffic elements but also topology relationships among lanes and between lanes and traffic elements simultaneously.\nIn this task, we use [OpenLane-V2 Score (OLS)](docs/metrics.md#openlane-topology) to evaluate model performance.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## Highlights of OpenLane-V2\n\n### Unifying Map Representations\n\nOne of the superior formulations in the bucket is [**Lane Segment**](/docs/features.md#map-element-bucket). It serves as a unifying and versatile representation of lanes, paving the way for multiple downstream applications. With the introduction of [**SD Map**](/docs/features.md#sd-map), the autonomous driving system is capable of utilizing these informative priors for achieving satisfactory performance in perception and reasoning.\n\nThe following table sums up a detailed comparison of different `lane formulations` to achieve various functionalities.\n\n\u003ctable\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd rowspan=\"2\"\u003eLane Formulation\u003c/td\u003e\n    \u003ctd colspan=\"8\"\u003eFunctionality\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003e3D Space\u003c/td\u003e\n    \u003ctd\u003eLaneline Cateogry\u003c/td\u003e\n    \u003ctd\u003eLane Direction\u003c/td\u003e\n    \u003ctd\u003eDrivable Area\u003c/td\u003e\n    \u003ctd\u003eLane-level Drivable Area\u003c/td\u003e\n    \u003ctd\u003eLane-lane Topology\u003c/td\u003e\n    \u003ctd\u003eBind to Traffic Element\u003c/td\u003e\n    \u003ctd\u003eLaneline-less\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003e2D Laneline\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003e3D Laneline\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003eOnline (pseudo) HD Map\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003eLane Centerline\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr align=\"center\"\u003e\n    \u003ctd\u003e\u003cb\u003eLane Segment\u003c/b\u003e (newly released)\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n    \u003ctd\u003e✅\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n\u003e - 3D Space: whether the perceived entities are represented in the 3D space.\n\u003e - Laneline Category: categories of the visible laneline, such as solid and dash.\n\u003e - Lane Direction: the driving direction that vehicles need to follow in a particular lane.\n\u003e - Drivable Area: the entire area where vehicles are allowed to drive.\n\u003e - Lane-level Drivable Area: drivable area of a single lane, which restricts vehicles from trespassing neighboring lanes.\n\u003e - Lane-lane Topology: connectivity of lanes that builds the lane network to provide routing information.\n\u003e - Bind to Traffic Element: correspondence to traffic elements, which provide regulations according to traffic rules.\n\u003e - Laneline-less: the ability to provide guidance in areas where no visible laneline is available, such as intersections.\n\n\n### Introducing 3D Laneline \nPrevious datasets annotate lanes on images in the perspective view. Such a type of 2D annotation is insufficient to fulfill real-world requirements.\nFollowing the [OpenLane-V1](https://github.com/OpenDriveLab/OpenLane) practice, we annotate [**lanes in 3D space**](/docs/features.md#3d-lane-detection) to reflect the geometric properties in the real 3D world.\n\n### Recognizing Extremely Small Traffic Elements\nNot only preventing collision but also facilitating efficiency is essential. \nVehicles follow predefined traffic rules for self-disciplining and cooperating with others to ensure a safe and efficient traffic system.\n[**Traffic elements**](/docs/features.md#traffic-element-recognition) on the roads, such as traffic lights and road signs, provide practical and real-time information.\n\n### Topology Reasoning between Lane and Road Elements \nA traffic element is only valid for its corresponding lanes. \nFollowing the wrong signals would be catastrophic. \nAlso, lanes have their predecessors and successors to build the map. \nAutonomous vehicles are required to **reason** about the [**topology relationships**](/docs/features.md#topology-recognition) to drive in the right way.\n\n\u003c!--\n### Data scale and diversity matters - building on top of renowned Benchmarks\nExperience from the sunny day does not apply to the dancing snowflakes.\nFor machine learning, data is the must-have food.\nWe provide annotations on data collected in various cities, from Austin to Singapore and from Boston to Miami.\nThe **diversity** of data enables models to generalize in different atmospheres and landscapes.\n--\u003e\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## Getting Started\n- [Download Data](/docs/getting_started.md#download-data)\n- [Install Devkit](/docs/getting_started.md#install-devkit)\n- [Prepare Dataset](/docs/getting_started.md#prepare-dataset)\n- [Train a Model](/docs/getting_started.md#train-a-model)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## License \u0026 Citation\n\n\u003e Prior to using the OpenLane-V2 dataset, you should agree to the terms of use of the [nuScenes](https://www.nuscenes.org/nuscenes) and [Argoverse 2](https://www.argoverse.org/av2.html) datasets respectively.\n\u003e OpenLane-V2 is distributed under [CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0) license.\n\u003e All code within this repository is under [Apache License 2.0](./LICENSE).\n\nPlease use the following citation when referencing OpenLane-V2:\n\n```bibtex\n@inproceedings{wang2023openlanev2,\n  title={OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping}, \n  author={Wang, Huijie and Li, Tianyu and Li, Yang and Chen, Li and Sima, Chonghao and Liu, Zhenbo and Wang, Bangjun and Jia, Peijin and Wang, Yuting and Jiang, Shengyin and Wen, Feng and Xu, Hang and Luo, Ping and Yan, Junchi and Zhang, Wei and Li, Hongyang},\n  booktitle={NeurIPS},\n  year={2023}\n}\n\n@article{li2023toponet,\n  title={Graph-based Topology Reasoning for Driving Scenes},\n  author={Li, Tianyu and Chen, Li and Wang, Huijie and Li, Yang and Yang, Jiazhi and Geng, Xiangwei and Jiang, Shengyin and Wang, Yuting and Xu, Hang and Xu, Chunjing and Yan, Junchi and Luo, Ping and Li, Hongyang},\n  journal={arXiv preprint arXiv:2304.05277},\n  year={2023}\n}\n\n@inproceedings{li2023lanesegnet,\n  title={LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving},\n  author={Li, Tianyu and Jia, Peijin and Wang, Bangjun and Chen, Li and Jiang, Kun and Yan, Junchi and Li, Hongyang},\n  booktitle={ICLR},\n  year={2024}\n}\n```\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\n## Related Resources\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n\n- [DriveAGI](https://github.com/OpenDriveLab/DriveAGI) | [DriveLM](https://github.com/OpenDriveLab/DriveLM) | [OpenScene](https://github.com/OpenDriveLab/OpenScene)\n- [TopoNet](https://github.com/OpenDriveLab/TopoNet) | [LaneSegNet](https://github.com/OpenDriveLab/LaneSegNet)\n- [PersFormer](https://github.com/OpenDriveLab/PersFormer_3DLane) | [OpenLane](https://github.com/OpenDriveLab/OpenLane)\n- [BEV Perception Survey \u0026 Recipe](https://github.com/OpenDriveLab/BEVPerception-Survey-Recipe) | [BEVFormer](https://github.com/fundamentalvision/BEVFormer)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendrivelab%2Fopenlane-v2","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopendrivelab%2Fopenlane-v2","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendrivelab%2Fopenlane-v2/lists"}