{"id":13441700,"url":"https://github.com/OpenDriveLab/DriveAGI","last_synced_at":"2025-03-20T12:32:27.226Z","repository":{"id":178951375,"uuid":"632101482","full_name":"OpenDriveLab/DriveAGI","owner":"OpenDriveLab","description":"[CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving \u0026 Foundation Models in Autonomous System","archived":false,"fork":false,"pushed_at":"2024-09-09T05:07:11.000Z","size":14001,"stargazers_count":527,"open_issues_count":5,"forks_count":21,"subscribers_count":27,"default_branch":"main","last_synced_at":"2024-09-09T17:56:59.818Z","etag":null,"topics":["autonomous-driving","embodied-ai","foundation-model","general-artificial-intelligence","policy-learning"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2403.09630","language":"Python","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":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},"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":"2023-04-24T17:59:42.000Z","updated_at":"2024-09-09T05:07:14.000Z","dependencies_parsed_at":null,"dependency_job_id":"ad526c2a-945e-4867-8b5e-564b3012cd9e","html_url":"https://github.com/OpenDriveLab/DriveAGI","commit_stats":null,"previous_names":["opendrivelab/driveagi"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FDriveAGI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FDriveAGI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FDriveAGI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OpenDriveLab%2FDriveAGI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OpenDriveLab","download_url":"https://codeload.github.com/OpenDriveLab/DriveAGI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221760117,"owners_count":16876356,"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":["autonomous-driving","embodied-ai","foundation-model","general-artificial-intelligence","policy-learning"],"created_at":"2024-07-31T03:01:37.137Z","updated_at":"2025-03-20T12:32:27.219Z","avatar_url":"https://github.com/OpenDriveLab.png","language":"Python","funding_links":["https://github.com/sponsors/OpenDriveLab"],"categories":["Python","General-Purpose / Sequential / Token Feature Sequence"],"sub_categories":["2024"],"readme":"# DriveAGI\nThis is **\"The One\"** project that [**`OpenDriveLab`**](https://opendrivelab.com/) is committed to contribute to the community, providing some thought and general picture of how to embrace `foundation models` into autonomous driving.\n\n## Table of Contents\n- [NEWS](#news)\n- [At A Glance](#at-a-glance)\n- 🚀 [Vista](#vista) (NeurIPS 2024)\n- ⭐ [GenAD: OpenDV Dataset](#opendv) (CVPR 2024 Hightlight)\n- ⭐ [DriveLM](#drivelm) (ECCV 2024 Oral)\n- [DriveData Survey](#drivedata-survey)\n  \u003c!-- - [Abstract](#abstract)\n  - [Related Work Collection](#related-work-collection) --\u003e\n- [OpenScene](#openscene)\n- [OpenLane-V2 Update](#openlane-v2-update)\n\n\n\n## NEWS\n\u003cdetails\u003e\n\n**\u003cfont color=\"red\"\u003e[ NEW❗️]\u003c/font\u003e `2024/09/08`** We released a mini version of `OpenDV-YouTube`, containing **25 hours** of driving videos. Feel free to try the mini subset by following instructions at [OpenDV-mini](https://github.com/OpenDriveLab/DriveAGI/blob/main/opendv/README.md)!\n\n**`2024/05/28`** We released our latest research, [Vista](#vista), a generalizable driving world model. It's capable of predicting high-fidelity and long-horizon futures, executing multi-modal actions, and serving as a generalizable reward function to assess driving behaviors. \n\n\n**`2024/03/24`** `OpenDV-YouTube Update:` **Full suite of toolkits for OpenDV-YouTube** is now available, including data downloading and processing scripts, as well as language annotations. Please refer to [OpenDV-YouTube](https://github.com/OpenDriveLab/DriveAGI/tree/main/opendv).\n\n**`2024/03/15`** We released the complete video list of `OpenDV-YouTube`, a large-scale driving video dataset, for [GenAD](https://arxiv.org/abs/2403.09630) project. Data downloading and processing script, as well as language annotations, will be released next week. Stay tuned.\n\n**`2024/01/24`**\nWe are excited to announce some update to [our survey](#drivedata-survey) and would like to thank John Lambert, Klemens Esterle from the public community for their advice to improve the manuscript.\n\u003c/details\u003e\n\n\n## At A Glance\n\n\u003cdetails\u003e\nHere are some key components to construct a large foundation model curated for an autonomous system.\n\n![overview](assets/overview.png \"overview\")\n\n\nBelow we would like to share the latest update from our team on the **`DriveData`** side. We will release the detail of the **`DriveEngine`** and the **`DriveAGI`** in the future.\n\u003c/details\u003e\n\n## Vista\n\u003cdiv id=\"top\" align=\"center\"\u003e\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"assets/vista-teaser.gif\" width=\"1000px\" \u003e\n\u003c/p\u003e\n\u003c/div\u003e\n\n\u003e Simulated futures in a wide range of driving scenarios by [Vista](https://arxiv.org/abs/2405.17398). Best viewed on [demo page](https://vista-demo.github.io/).\n\n### [🌏 **A Generalizable Driving World Model with High Fidelity and Versatile Controllability**](https://arxiv.org/abs/2405.17398) (NeurIPS 2024)\n\n**Quick facts:**\n- Introducing the world's first **generalizable driving world model**.\n- Task: High-fidelity, action-conditioned, and long-horizon future prediction for driving scenes in the wild.\n- Dataset: [`OpenDV-YouTube`](https://github.com/OpenDriveLab/DriveAGI/tree/main/opendv), `nuScenes`\n- Code and model: https://github.com/OpenDriveLab/Vista\n- Video Demo: https://vista-demo.github.io\n- Related work: [Vista](https://arxiv.org/abs/2405.17398), [GenAD](https://arxiv.org/abs/2403.09630)\n\n```bibtex\n@inproceedings{gao2024vista,\n title={Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability}, \n author={Shenyuan Gao and Jiazhi Yang and Li Chen and Kashyap Chitta and Yihang Qiu and Andreas Geiger and Jun Zhang and Hongyang Li},\n booktitle={Advances in Neural Information Processing Systems (NeurIPS)},\n year={2024}\n}\n\n@inproceedings{yang2024genad,\n  title={{Generalized Predictive Model for Autonomous Driving}},\n  author={Jiazhi Yang and Shenyuan Gao and Yihang Qiu and Li Chen and Tianyu Li and Bo Dai and Kashyap Chitta and Penghao Wu and Jia Zeng and Ping Luo and Jun Zhang and Andreas Geiger and Yu Qiao and Hongyang Li},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},\n  year={2024}\n}\n```\n\n## GenAD: OpenDV Dataset \u003ca name=\"opendv\"\u003e\u003c/a\u003e\n![opendv](assets/opendv_examples.png)\n\u003e Examples of **real-world** driving scenarios in the OpenDV dataset, including urban, highway, rural scenes, etc.\n\n### [⭐ **Generalized Predictive Model for Autonomous Driving**](https://arxiv.org/abs/2403.09630) (**CVPR 2024, Highlight**)\n\n### [Paper](https://arxiv.org/abs/2403.09630) | [Video](https://www.youtube.com/watch?v=a4H6Jj-7IC0) | [Poster](assets/cvpr24_genad_poster.png) | [Slides](https://opendrivelab.github.io/content/GenAD_slides_with_vista.pdf)\n\n🎦 The **Largest Driving Video dataset** to date, containing more than **1700 hours** of real-world driving videos and being 300 times larger than the widely used nuScenes dataset.\n\n\n- **Complete video list** (under YouTube license): [OpenDV Videos](https://docs.google.com/spreadsheets/d/1bHWWP_VXeEe5UzIG-QgKFBdH7mNlSC4GFSJkEhFnt2I).\n  - The downloaded raw videos (`mostly 1080P`) consume about `3 TB` storage space. However, these hour-long videos cannot be directly applied for model training as they are extremely memory consuming.\n  - Therefore, we preprocess them into conseductive images which are more flexible and efficient to load during training. Processed images consumes about `24 TB` storage space in total.\n  - It's recommended to set up your experiments on a small subset, say **1/20** of the whole dataset. An official mini subset is also provided and you can refer to [**OpenDV-mini**](https://github.com/OpenDriveLab/DriveAGI/tree/main/opendv#about-opendv-youtube-and-opendv-mini) for details. After stablizing the training, you can then apply your method on the whole dataset and hope for the best 🤞.\n- \u003cfont color=\"red\"\u003e**[ New❗️]**\u003c/font\u003e **Mini subset**: [OpenDV-mini](https://github.com/OpenDriveLab/DriveAGI/tree/main/opendv).\n  - A mini version of `OpenDV-YouTube`. The raw videos consume about `44 GB` of storage space and the processed images will consume about `390 GB` of storage space.\n- **Step-by-step instruction for data preparation**: [OpenDV-YouTube](https://github.com/OpenDriveLab/DriveAGI/tree/main/opendv/README.md).\n- **Language annotation for OpenDV-YouTube**: [OpenDV-YouTube-Language](https://huggingface.co/datasets/OpenDriveLab/OpenDV-YouTube-Language).\n\n\n**Quick facts:**\n- Task: large-scale video prediction for driving scenes.\n- Data source: `YouTube`, with careful collection and filtering process.\n- Diversity Highlights: 1700 hours of driving videos, covering more than 244 cities in 40 countries.\n- Related work: [GenAD](https://arxiv.org/abs/2403.09630) **`Accepted at CVPR 2024, Highlight`**\n- `Note`: Annotations for other public datasets in OpenDV-2K will not be released since we randomly sampled a subset of them in training, which are incomplete and hard to trace back to their origins (i.e., file name). Nevertheless, it's easy to reproduce the collection and annotation process on your own following [our paper]((https://arxiv.org/abs/2403.09630)).\n\n```bibtex\n@inproceedings{yang2024genad,\n  title={Generalized Predictive Model for Autonomous Driving},\n  author={Jiazhi Yang and Shenyuan Gao and Yihang Qiu and Li Chen and Tianyu Li and Bo Dai and Kashyap Chitta and Penghao Wu and Jia Zeng and Ping Luo and Jun Zhang and Andreas Geiger and Yu Qiao and Hongyang Li},\n  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},\n  year={2024}\n}\n```\n\n## DriveLM\nIntroducing the First benchmark on **Language Prompt for Driving**.\n\n**Quick facts:**\n- Task: given the language prompts as input, predict the trajectory in the scene\n- Origin dataset: `nuScenes`, `CARLA (To be released)`\n- Repo: https://github.com/OpenDriveLab/DriveLM, https://github.com/OpenDriveLab/ELM\n- Related work: [DriveLM](https://arxiv.org/abs/2312.14150), [ELM](https://arxiv.org/abs/2403.04593)\n- Related challenge: [Driving with Language AGC Challenge 2024](https://opendrivelab.com/challenge2024/#driving_with_language)\n\n\n## DriveData Survey\n\u003cdetails\u003e\n\n### Abstract\nWith the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem. In this survey, we provide a comprehensive analysis of more than 70 papers on the timeline, impact, challenges, and future trends in autonomous driving dataset.\n\n\u003e **Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future**\n\u003e - [English Version](https://arxiv.org/abs/2312.03408)\n\u003e - [Chinese Version](https://www.sciengine.com/SSI/doi/10.1360/SSI-2023-0313) **`Accepted at SCIENTIA SINICA Informationis (中文版)`**\n\n ```bib\n@article{li2024_driving_dataset_survey,\n  title = {Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future},\n  author = {Hongyang Li and Yang Li and Huijie Wang and Jia Zeng and Huilin Xu and Pinlong Cai and Li Chen and Junchi Yan and Feng Xu and Lu Xiong and Jingdong Wang and Futang Zhu and Chunjing Xu and Tiancai Wang and Fei Xia and Beipeng Mu and Zhihui Peng and Dahua Lin and Yu Qiao},\n  journal = {SCIENTIA SINICA Informationis},\n  year = {2024},\n  doi = {10.1360/SSI-2023-0313}\n}\n```\n\n\u003c!-- \u003e [Hongyang Li](https://lihongyang.info/)\u003csup\u003e1\u003c/sup\u003e, Yang Li\u003csup\u003e1\u003c/sup\u003e, [Huijie Wang](https://faikit.github.io/)\u003csup\u003e1\u003c/sup\u003e, [Jia Zeng](https://scholar.google.com/citations?user=kYrUfMoAAAAJ)\u003csup\u003e1\u003c/sup\u003e, Pinlong Cai\u003csup\u003e1\u003c/sup\u003e, Dahua Lin\u003csup\u003e1\u003c/sup\u003e, Junchi Yan\u003csup\u003e2\u003c/sup\u003e, Feng Xu\u003csup\u003e3\u003c/sup\u003e, Lu Xiong\u003csup\u003e4\u003c/sup\u003e, Jingdong Wang\u003csup\u003e5\u003c/sup\u003e, Futang Zhu\u003csup\u003e6\u003c/sup\u003e, Kai Yan\u003csup\u003e7\u003c/sup\u003e, Chunjing Xu\u003csup\u003e8\u003c/sup\u003e, Tiancai Wang\u003csup\u003e9\u003c/sup\u003e, Beipeng Mu\u003csup\u003e10\u003c/sup\u003e, Shaoqing Ren\u003csup\u003e11\u003c/sup\u003e, Zhihui Peng\u003csup\u003e12\u003c/sup\u003e, Yu Qiao\u003csup\u003e1\u003c/sup\u003e\n\u003e \n\u003e \u003csup\u003e1\u003c/sup\u003e Shanghai AI Lab, \u003csup\u003e2\u003c/sup\u003e Shanghai Jiao Tong University, \u003csup\u003e3\u003c/sup\u003e Fudan University, \u003csup\u003e4\u003c/sup\u003e Tongji University, \u003csup\u003e5\u003c/sup\u003e Baidu, \u003csup\u003e6\u003c/sup\u003e BYD, \u003csup\u003e7\u003c/sup\u003e Changan, \u003csup\u003e8\u003c/sup\u003e Huawei, \u003csup\u003e9\u003c/sup\u003e Megvii Technology, \u003csup\u003e10\u003c/sup\u003e Meituan, \u003csup\u003e11\u003c/sup\u003e Nio Automotive, \u003csup\u003e12\u003c/sup\u003e Agibot\n\u003e --\u003e\n\n![overview](assets/Drivedata_overview.jpg \"Drivedata_overview\")\n\u003eCurrent autonomous driving datasets can broadly be categorized into two generations since the 2010s. We define the Impact (y-axis) of a dataset based on sensor configuration, input modality, task category, data scale, ecosystem, etc.\n\n![overview](assets/Drivedata_timeline.jpg \"Drivedata_timeline\")\n\n### Related Work Collection \n\nWe present comprehensive paper collections, leaderboards, and challenges.(Click to expand)\n\n\u003cdetails\u003e\n\u003csummary\u003eChallenges and Leaderboards\u003c/summary\u003e\n\n\u003ctable\u003e\n\u003ccapital\u003e\u003c/capital\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \u003cth \u003eTitle\u003c/th\u003e\n    \u003cth \u003eHost\u003c/th\u003e\n    \u003cth \u003eYear\u003c/th\u003e\n    \u003cth \u003eTask\u003c/th\u003e\n    \u003cth \u003eEntry\u003c/th\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=7 \u003e\u003ca href=\"https://opendrivelab.com/AD23Challenge.html\" target=\"_blank\" title=\"Autonomous Driving Challenge\"\u003eAutonomous Driving Challenge\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=7 \u003e OpenDriveLab\u003c/td\u003e\n      \u003ctd rowspan=7 \u003eCVPR2023\u003c/td\u003e\n       \u003ctd\u003ePerception / OpenLane Topology\u003c/td\u003e\n    \t\u003ctd rowspan=7\u003e 111 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Online HD Map Construction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / 3D Occupancy Prediction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n        \u003ctd\u003ePrediction \u0026 Planning / nuPlan Planning\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=23 \u003e\u003ca href=\"https://waymo.com/open/challenges/\" target=\"_blank\" title=\"Waymo Open Dataset\nChallenges\"\u003eWaymo Open Dataset Challenges\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=23 \u003e Waymo\u003c/td\u003e\n      \u003ctd rowspan=8\u003eCVPR2023\u003c/td\u003e\n       \u003ctd\u003ePerception / 2D Video Panoptic Segmentation\u003c/td\u003e\n    \t\u003ctd rowspan=8\u003e 35 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Pose Estimation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / Motion Prediction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \u003ctd\u003ePrediction / Sim Agents\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \n      \u003ctd rowspan=8\u003eCVPR2022\u003c/td\u003e\n       \u003ctd\u003ePrediction / Motion Prediction\u003c/td\u003e\n    \t\u003ctd rowspan=8\u003e 128 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / Occupancy and Flow Prediction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / 3D Semantic Segmentation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / 3D Camera-only Detection\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \n \u003ctd rowspan=7\u003eCVPR2021\u003c/td\u003e\n       \u003ctd\u003ePrediction / Motion Prediction\u003c/td\u003e\n    \t\u003ctd rowspan=7\u003e 115 \u003c/td\u003e\n  \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / Interaction Prediction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Real-time 3D Detection\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Real-time 2D Detection\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=19 \u003e\u003ca href=\"https://www.argoverse.org/tasks.html\" target=\"_blank\" title=\"Argoverse\nChallenges\"\u003eArgoverse Challenges\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=19 \u003e Argoverse\u003c/td\u003e\n      \u003ctd rowspan=8\u003eCVPR2023\u003c/td\u003e\n       \u003ctd\u003ePrediction / Multi-agent Forecasting\u003c/td\u003e\n    \t\u003ctd rowspan=8\u003e 81 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception \u0026 Prediction / Unified Sensorbased Detection, Tracking, and Forecasting\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / LiDAR Scene Flow\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / 3D Occupancy Forecasting\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n  \u003ctd rowspan=6\u003eCVPR2022\u003c/td\u003e\n       \u003ctd\u003ePerception / 3D Object Detection\u003c/td\u003e\n    \t\u003ctd rowspan=6\u003e 81 \u003c/td\u003e \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / Motion Forecasting\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Stereo Depth Estimation\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \n      \u003ctd rowspan=5\u003eCVPR2021\u003c/td\u003e\n       \u003ctd\u003ePerception / Stereo Depth Estimation\u003c/td\u003e\n    \t\u003ctd rowspan=5\u003e 368 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / Motion Forecasting\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / Streaming 2D Detection\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=5 \u003e\u003ca href=\"https://carlachallenge.org/\" target=\"_blank\" title=\"CARLA Autonomous Driving Challenge\"\u003eCARLA Autonomous Driving Challenge\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=5 \u003e CARLA Team, Intel\u003c/td\u003e\n      \u003ctd rowspan=2 \u003e2023\u003c/td\u003e\n      \u003ctd\u003ePlanning / CARLA AD Challenge 2.0\u003c/td\u003e\n    \t\u003ctd rowspan=2\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd rowspan=2 \u003eNeurIPS2022\u003c/td\u003e\n       \u003ctd\u003ePlanning / CARLA AD Challenge 1.0\u003c/td\u003e\n       \u003ctd rowspan=2\u003e 19 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd rowspan=1 \u003eNeurIPS2021\u003c/td\u003e\n       \u003ctd\u003ePlanning / CARLA AD Challenge 1.0\u003c/td\u003e\n       \u003ctd rowspan=1\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=7 \u003e\u003ca href=\"https://iacc.pazhoulab-huangpu.com/\" target=\"_blank\" title=\"粤港澳大湾区\n      （黄埔）国际算法算例大赛\"\u003e粤港澳大湾区\n（黄埔）国际算法算例大赛\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=7\u003e 琶洲实验室\u003c/td\u003e\n      \u003ctd rowspan=4\u003e2023\u003c/td\u003e\n       \u003ctd\u003e感知 / 跨场景单目深度估计\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003e感知 / 路侧毫米波雷达标定和目标跟踪\u003c/td\u003e\n       \u003ctd\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=3\u003e2022\u003c/td\u003e\n       \u003ctd\u003e感知 / 路侧三维感知算法\u003c/td\u003e\n       \u003ctd\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003e感知 / 街景图像店面招牌文字识别\u003c/td\u003e\n       \u003ctd\u003e - \u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=9 \u003e\u003ca href=\"https://driving-olympics.ai/\" target=\"_blank\" title=\"AI Driving Olympics\"\u003eAI Driving Olympics\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=9 \u003e ETH Zurich, University of Montreal,Motional\u003c/td\u003e\n      \u003ctd\u003e NeurIP2021 \u003c/td\u003e\n      \u003ctd rowspan=1\u003ePerception / nuScenes Panoptic\u003c/td\u003e\n    \t\u003ctd\u003e 11 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=7\u003eICRA2021\u003c/td\u003e\n       \u003ctd\u003ePerception / nuScenes Detection\u003c/td\u003e\n       \u003ctd rowspan=7\u003e 456 \u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / nuScenes Tracking\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePrediction / nuScenes Prediction\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003ePerception / nuScenes LiDAR Segmentation\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=1 \u003e\u003ca href=\"https://cg.cs.tsinghua.edu.cn/jittor/news/2021-1-22-13-14-comp/\" target=\"_blank\" title=\"计图 (Jittor)人工智能算法挑战赛\"\u003e计图 (Jittor)人工智能算法挑战赛\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=1 \u003e 国家自然科学基金委信息科学部\u003c/td\u003e\n      \u003ctd\u003e 2021 \u003c/td\u003e\n      \u003ctd rowspan=1\u003e感知 / 交通标志检测\u003c/td\u003e\n    \t\u003ctd\u003e 37 \u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd rowspan=1 \u003e\u003ca href=\"https://www.cvlibs.net/datasets/kitti/\" target=\"_blank\" title=\"KITTI Vision Benchmark Suite\"\u003eKITTI Vision Benchmark Suite\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd rowspan=1 \u003e University of Tübingen \u003c/td\u003e\n      \u003ctd\u003e 2012 \u003c/td\u003e\n      \u003ctd rowspan=1\u003ePerception / Stereo, Flow, Scene Flow, Depth,\nOdometry, Object, Tracking, Road, Semantics\u003c/td\u003e\n    \t\u003ctd\u003e 5,610 \u003c/td\u003e\n\u003c/tr\u003e\n\n\u003c/table\u003e\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003ePerception Datasets\u003c/summary\u003e\n\n\u003ctable\u003e\n\u003ccapital\u003e\u003c/capital\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \u003cth rowspan=3 colspan=1\u003eDataset\u003c/th\u003e\n    \u003cth rowspan=3 \u003eYear\u003c/td\u003e\n    \u003cth  align=\"middle\" colspan=3 \u003eDiversity\u003c/th\u003e\n    \u003cth  align=\"middle\" colspan=3 \u003eSensor\u003c/th\u003e\n    \u003cth rowspan=3 colspan=1\u003eAnnotation\u003c/th\u003e\n    \u003cth rowspan=3 colspan=1\u003ePaper\u003c/th\u003e\n\u003c/tr\u003e \n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n  \t  \u003cth\u003e Scenes\u003c/th\u003e\n    \t\u003cth\u003e Hours \u003c/th\u003e\n    \t\u003cth\u003e Region \u003c/th\u003e\n  \t  \u003cth\u003e Camera\u003c/th\u003e\n    \t\u003cth\u003e Lidar \u003c/th\u003e\n    \t\u003cth\u003e Other \u003c/th\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.cvlibs.net/datasets/kitti/\" target=\"_blank\" title=\"Homepage\"\u003eKITTI\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2012\u003c/td\u003e\n    \t\u003ctd\u003e 50 \u003c/td\u003e\n    \t\u003ctd\u003e 6 \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003e Font-view \u003c/td\u003e\n      \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u0026 3D BBox\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.cvlibs.net/publications/Geiger2012CVPR.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.cityscapes-dataset.com/\" target=\"_blank\" title=\"Homepage\"\u003eCityscapes\u003c/a\u003e\u003c/td\u003e  \t  \u003ctd\u003e 2016\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003e Font-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D Seg\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1604.01685\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"http://ww1.6d-vision.com/lostandfounddataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eLost and Found\u003c/a\u003e\u003c/td\u003e  \t  \u003ctd\u003e 2016\u003c/td\u003e\n    \t\u003ctd\u003e 112 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e Font-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D Seg\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1609.04653\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://eval-vistas.mapillary.com/\" target=\"_blank\" \n      title=\"Homepage\"\u003eMapillary\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2016\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e Global\u003c/td\u003e\n    \t\u003ctd\u003e Street-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D Seg\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content_ICCV_2017/papers/Neuhold_The_Mapillary_Vistas_ICCV_2017_paper.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"http://sensors.ini.uzh.ch/news_page/DDD17.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eDDD17\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2017\u003c/td\u003e\n    \t\u003ctd\u003e 36\u003c/td\u003e\n    \t\u003ctd\u003e 12 \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 CAN-bus \u0026 Event Camera\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1711.01458.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/ApolloScapeAuto/dataset-api\" target=\"_blank\" \n      title=\"Homepage\"\u003eApolloscape\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2016\u003c/td\u003e\n    \t\u003ctd\u003e 103\u003c/td\u003e\n    \t\u003ctd\u003e 2.5 \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u003c/td\u003e\n      \u003ctd\u003e 3D BBox \u0026 2D Seg\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1803.06184.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/JinkyuKimUCB/BDD-X-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eBDD-X\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2018\u003c/td\u003e\n    \t\u003ctd\u003e 6984\u003c/td\u003e\n    \t\u003ctd\u003e 77 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗ \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003eLanguage\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1807.11546.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://usa.honda-ri.com/hdd\" target=\"_blank\" \n      title=\"Homepage\"\u003eHDD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2018\u003c/td\u003e\n    \t\u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e 104 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u0026 CAN-bus \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1811.02307v1.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://idd.insaan.iiit.ac.in/dataset/details/\" target=\"_blank\" \n      title=\"Homepage\"\u003eIDD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2018\u003c/td\u003e\n    \t\u003ctd\u003e 182\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1811.10200v1.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"http://semantic-kitti.org/\" target=\"_blank\" \n      title=\"Homepage\"\u003eSemanticKITTI\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019\u003c/td\u003e\n    \t\u003ctd\u003e 50\u003c/td\u003e\n    \t\u003ctd\u003e 6 \u003c/td\u003e\n  \t  \u003ctd\u003e EU \u003c/td\u003e\n    \t\u003ctd\u003e ✗ \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1904.01416.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/valeoai/WoodScape\" target=\"_blank\" \n      title=\"Homepage\"\u003eWoodscape\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e Global\u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u0026 CAN-bus \u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1905.01489.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://drivingstereo-dataset.github.io/\" target=\"_blank\" \n      title=\"Homepage\"\u003eDrivingStereo\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 42\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e AS \u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://ieeexplore.ieee.org/document/8954165/\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/Robotics-BUT/Brno-Urban-Dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eBrno-Urban\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 67\u003c/td\u003e\n    \t\u003ctd\u003e 10 \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u0026 Infrared Camera \u003c/td\u003e\n      \u003ctd\u003e -\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1909.06897.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/I2RDL2/ASTAR-3D\" target=\"_blank\" \n      title=\"Homepage\"\u003eA*3D\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e 55 \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e 3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1909.07541v1.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/talk2car/Talk2Car\" target=\"_blank\" \n      title=\"Homepage\"\u003eTalk2Car\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 850\u003c/td\u003e\n    \t\u003ctd\u003e 283.3 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003eLanguage \u0026 3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1909.10838.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://data.vision.ee.ethz.ch/arunv/personal/talk2nav.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eTalk2Nav\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 10714\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e Sim\u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003eLanguage \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1910.02029.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/aras62/PIEPredict\" target=\"_blank\" \n      title=\"Homepage\"\u003ePIE\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e 6 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content_ICCV_2019/papers/Rasouli_PIE_A_Large-Scale_Dataset_and_Models_for_Pedestrian_Intention_Estimation_ICCV_2019_paper.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/weisongwen/UrbanLoco\" target=\"_blank\" \n      title=\"Homepage\"\u003eUrbanLoco\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 13\u003c/td\u003e\n    \t\u003ctd\u003e -\u003c/td\u003e\n  \t  \u003ctd\u003eAS \u0026 NA\u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e IMU \u003c/td\u003e\n      \u003ctd\u003e- \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1912.09513.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://usa.honda-ri.com/titan\" target=\"_blank\" \n      title=\"Homepage\"\u003eTITAN\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 700\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗   \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/2003.13886.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://usa.honda-ri.com/H3D\" target=\"_blank\" \n      title=\"Homepage\"\u003eH3D \u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 160 \u003c/td\u003e\n    \t\u003ctd\u003e 0.77 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u003c/td\u003e\n      \u003ctd\u003e- \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1903.01568.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.a2d2.audi/a2d2/en/download.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eA2D2\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2020 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e 5.6  \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003e 360°  \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u0026 CAN-bus\u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/2004.06320.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/valeoai/carrada_dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eCARRADA\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2020 \u003c/td\u003e\n    \t\u003ctd\u003e 30  \u003c/td\u003e\n    \t\u003ctd\u003e 0.3 \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e Front-view  \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e Radar\u003c/td\u003e\n      \u003ctd\u003e3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2005.01456.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://data.mendeley.com/datasets/766ygrbt8y/3\" target=\"_blank\" \n      title=\"Homepage\"\u003eDAWN\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019  \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e Global\u003c/td\u003e\n    \t\u003ctd\u003e Front-view  \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2008.05402.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/pmwenzel/4seasons-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003e4Seasons\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019\u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e Front-view  \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU\u003c/td\u003e\n      \u003ctd\u003e- \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2009.06364.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/sauradip/night_image_semantic_segmentation#Urban%20Night%20Driving%20Dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eUNDD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e -\u003c/td\u003e\n    \t\u003ctd\u003e Front-view  \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://ieeexplore.ieee.org/document/8803299\n\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"http://www.poss.pku.edu.cn/\" target=\"_blank\" \n      title=\"Homepage\"\u003eSemanticPOSS\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2020 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e ✗  \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u003c/td\u003e\n      \u003ctd\u003e3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2002.09147.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/WeikaiTan/Toronto-3D\" target=\"_blank\" \n      title=\"Homepage\"\u003eToronto-3D\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2020 \u003c/td\u003e\n    \t\u003ctd\u003e 4 \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e ✗ \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content_CVPRW_2020/papers/w11/Tan_Toronto-3D_A_Large-Scale_Mobile_LiDAR_Dataset_for_Semantic_Segmentation_of_CVPRW_2020_paper.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/gurkirt/road-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eROAD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021 \u003c/td\u003e\n    \t\u003ctd\u003e 22 \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e EU\u003c/td\u003e\n    \t\u003ctd\u003eFront-view \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u0026 Topology \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2102.11585.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/bassam-motional/Reasonable-Crowd\" target=\"_blank\" \n      title=\"Homepage\"\u003eReasonable Crowd\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e Sim\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003eLanguage \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2107.13507.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://gamma.umd.edu/researchdirections/autonomousdriving/meteor/\" target=\"_blank\" \n      title=\"Homepage\"\u003eMETEOR\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021 \u003c/td\u003e\n    \t\u003ctd\u003e 1250 \u003c/td\u003e\n    \t\u003ctd\u003e 20.9  \u003c/td\u003e\n  \t  \u003ctd\u003e AS\u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e GPS  \u003c/td\u003e\n      \u003ctd\u003eLanguage \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2109.07648.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/scaleapi/pandaset-devkit\" target=\"_blank\" \n      title=\"Homepage\"\u003ePandaSet\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021 \u003c/td\u003e\n    \t\u003ctd\u003e 179 \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e NA\u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u003c/td\u003e\n      \u003ctd\u003e3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2112.12610.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/ENSTA-U2IS/MUAD-Dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eMUAD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2022 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e Sim \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D Seg\u0026 2D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2203.01437.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://mucar3.de/iros2022-ppniv-tas-nir/\" target=\"_blank\" \n      title=\"Homepage\"\u003eTAS-NIR\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2022 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗   \u003c/td\u003e\n    \t\u003ctd\u003eInfrared Camera \u003c/td\u003e\n      \u003ctd\u003e2D Seg\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2212.09368.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/LiDAR-Perception/LiDAR-CS\" target=\"_blank\" \n      title=\"Homepage\"\u003eLiDAR-CS\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2022 \u003c/td\u003e\n    \t\u003ctd\u003e 6 \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e Sim \u003c/td\u003e\n    \t\u003ctd\u003e ✗  \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2301.12515.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://wilddash.cc/\" target=\"_blank\" \n      title=\"Homepage\"\u003eWildDash \u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2022 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e -  \u003c/td\u003e\n  \t  \u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e Front-view \u003c/td\u003e\n      \u003ctd\u003e ✗   \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content_ECCV_2018/papers/Oliver_Zendel_WildDash_-_Creating_ECCV_2018_paper.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/OpenDriveLab/OpenScene\" target=\"_blank\" \n      title=\"Homepage\"\u003eOpenScene\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2023 \u003c/td\u003e\n    \t\u003ctd\u003e 1000 \u003c/td\u003e\n    \t\u003ctd\u003e 5.5  \u003c/td\u003e\n  \t  \u003ctd\u003e AS \u0026 NA\u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✗   \u003c/td\u003e\n    \t\u003ctd\u003e \u003c/td\u003e\n      \u003ctd\u003e3D Occ \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2211.15654.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://zod.zenseact.com/\" target=\"_blank\" \n      title=\"Homepage\"\u003eZOD\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2023 \u003c/td\u003e\n    \t\u003ctd\u003e 1473 \u003c/td\u003e\n    \t\u003ctd\u003e 8.2  \u003c/td\u003e\n  \t  \u003ctd\u003e EU   \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓   \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 IMU \u0026 CAN-bus \u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 2D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2305.02008\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.nuscenes.org/\" target=\"_blank\" \n      title=\"Homepage\"\u003enuScenes\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 1000 \u003c/td\u003e\n    \t\u003ctd\u003e 5.5  \u003c/td\u003e\n  \t  \u003ctd\u003e AS \u0026 NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e GPS \u0026 CAN-bus \u0026 Radar \u0026 HDMap\u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1903.11027.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.argoverse.org/av1.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eArgoverse V1\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 324k  \u003c/td\u003e\n    \t\u003ctd\u003e320   \u003c/td\u003e\n  \t  \u003ctd\u003e   NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e HDMap\u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/1911.02620.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/waymo-research/waymo-open-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eWaymo\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2019 \u003c/td\u003e\n    \t\u003ctd\u003e 1000 \u003c/td\u003e\n    \t\u003ctd\u003e6.4  \u003c/td\u003e\n  \t  \u003ctd\u003e NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e2D BBox \u0026 3D BBox \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1912.04838.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/autonomousvision/kitti360Scripts\" target=\"_blank\" \n      title=\"Homepage\"\u003eKITTI-360\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2020 \u003c/td\u003e\n    \t\u003ctd\u003e 366  \u003c/td\u003e\n    \t\u003ctd\u003e 2.5  \u003c/td\u003e\n  \t  \u003ctd\u003e EU \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e3D BBox \u0026 3D Seg \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2109.13410.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://once-for-auto-driving.github.io/index.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eONCE\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021  \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e 144  \u003c/td\u003e\n  \t  \u003ctd\u003e AS  \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e3D BBox  \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/2106.11037.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.nuscenes.org/nuplan\" target=\"_blank\" \n      title=\"Homepage\"\u003enuPlan \u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2021 \u003c/td\u003e\n    \t\u003ctd\u003e - \u003c/td\u003e\n    \t\u003ctd\u003e 120  \u003c/td\u003e\n  \t  \u003ctd\u003e AS \u0026 NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e3D BBox    \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2106.11810.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.argoverse.org/av2.html\" target=\"_blank\" \n      title=\"Homepage\"\u003eArgoverse V2\u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2022 \u003c/td\u003e\n    \t\u003ctd\u003e 1000 \u003c/td\u003e\n    \t\u003ctd\u003e 4  \u003c/td\u003e\n  \t  \u003ctd\u003e   NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✓  \u003c/td\u003e\n    \t\u003ctd\u003e  HDMap\u003c/td\u003e\n      \u003ctd\u003e3D BBox  \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/pdf/2301.00493.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/OpenDriveLab/DriveLM\" target=\"_blank\" \n      title=\"Homepage\"\u003eDriveLM \u003c/a\u003e\u003c/td\u003e  \t  \n      \u003ctd\u003e 2023 \u003c/td\u003e\n    \t\u003ctd\u003e 1000 \u003c/td\u003e\n    \t\u003ctd\u003e 5.5  \u003c/td\u003e\n  \t  \u003ctd\u003e AS \u0026 NA \u003c/td\u003e\n    \t\u003ctd\u003e 360° \u003c/td\u003e\n      \u003ctd\u003e ✗  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003eLanguage \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/OpenDriveLab/DriveLM\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n\u003ctr align=\"middle\"\u003e\n\u003c/table\u003e\n\n\u003c/table\u003e\n\u003cp align=\"right\"\u003e(\u003ca href=\"#top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003eMapping Datasets\u003c/summary\u003e\n\n\u003ctable\u003e\n\u003ccapital\u003e\u003c/capital\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \u003cth rowspan=3 colspan=1\u003eDataset\u003c/td\u003e\n    \u003cth rowspan=3 \u003eYear\u003c/td\u003e\n    \u003cth  align=\"middle\" colspan=2 \u003eDiversity\u003c/th\u003e\n    \u003cth  align=\"middle\" colspan=2 \u003eSensor\u003c/th\u003e\n    \u003cth  align=\"middle\" colspan=4 \u003eAnnotation\u003c/th\u003e\n    \u003cth rowspan=3 colspan=1\u003ePaper\u003c/th\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n  \t  \u003cth\u003e Scenes\u003c/th\u003e\n    \t\u003cth\u003e Frames \u003c/th\u003e\n  \t  \u003cth\u003e Camera\u003c/th\u003e\n    \t\u003cth\u003e Lidar \u003c/th\u003e\n    \t\u003cth\u003e Type \u003c/th\u003e\n    \t\u003cth\u003e Space \u003c/th\u003e\n    \t\u003cth\u003e Inst. \u003c/th\u003e\n    \t\u003cth\u003e Track \u003c/th\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.cvlibs.net/datasets/kitti/\" target=\"_blank\" title=\"Homepage\"\u003eCaltech Lanes\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2008\u003c/td\u003e\n      \u003ctd\u003e4\u003c/td\u003e\n    \t\u003ctd\u003e 1224/1224 \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.cvlibs.net/datasets/kitti/\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/SeokjuLee/VPGNet\" target=\"_blank\" title=\"Homepage\"\u003eVPG\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2017\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n    \t\u003ctd\u003e 20K/20K \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content_iccv_2017/html/Lee_VPGNet_Vanishing_Point_ICCV_2017_paper.html\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/TuSimple/tusimple-benchmark\" target=\"_blank\" title=\"Homepage\"\u003eTUsimple\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2017\u003c/td\u003e\n      \u003ctd\u003e6.4K\u003c/td\u003e\n    \t\u003ctd\u003e 6.4K/128K \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/TuSimple/tusimple-benchmark\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://xingangpan.github.io/projects/CULane.html\" target=\"_blank\" title=\"Homepage\"\u003eCULane\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2018\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n    \t\u003ctd\u003e 133K/133K \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1712.06080.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/ApolloScapeAuto/dataset-api\" target=\"_blank\" title=\"Homepage\"\u003eApolloScape\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2018 \u003c/td\u003e\n      \u003ctd\u003e235\u003c/td\u003e\n    \t\u003ctd\u003e115K/115K\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✓\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/1803.06184.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://unsupervised-llamas.com/llamas/\" target=\"_blank\" title=\"Homepage\"\u003eLLAMAS\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2019\u003c/td\u003e\n      \u003ctd\u003e14\u003c/td\u003e\n    \t\u003ctd\u003e 79K/100K  \u003c/td\u003e\n    \t\u003ctd\u003e Front-view Image \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e Laneline \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://ieeexplore.ieee.org/document/9022318\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/yuliangguo/Pytorch_Generalized_3D_Lane_Detection\" target=\"_blank\" title=\"Homepage\"\u003e3D Synthetic\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2020\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n    \t\u003ctd\u003e 10K/10K  \u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2003.10656.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/SoulmateB/CurveLanes\" target=\"_blank\" title=\"Homepage\"\u003eCurveLanes\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2020\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n    \t\u003ctd\u003e 150K/150K  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2007.12147.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/yujun0-0/mma-net\" target=\"_blank\" title=\"Homepage\"\u003eVIL-100\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2021 \u003c/td\u003e\n      \u003ctd\u003e100 \u003c/td\u003e\n    \t\u003ctd\u003e 10K/10K  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e  PV  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✗\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2108.08482.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/OpenDriveLab/OpenLane\" target=\"_blank\" title=\"Homepage\"\u003eOpenLane-V1\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2022\u003c/td\u003e\n      \u003ctd\u003e1K \u003c/td\u003e\n    \t\u003ctd\u003e 200K/200K  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n      \u003ctd\u003e  3D  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2203.11089.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://once-3dlanes.github.io/\" target=\"_blank\" title=\"Homepage\"\u003eONCE-3DLane\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2022 \u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n    \t\u003ctd\u003e 211K/211K  \u003c/td\u003e\n    \t\u003ctd\u003e  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e   \u003c/td\u003e\n      \u003ctd\u003e  3D \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e-\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://openaccess.thecvf.com/content/CVPR2022/papers/Yan_ONCE-3DLanes_Building_Monocular_3D_Lane_Detection_CVPR_2022_paper.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003e\u003ca href=\"https://github.com/OpenDriveLab/OpenLane-V2\" target=\"_blank\" title=\"Homepage\"\u003eOpenLane-V2\u003c/a\u003e\u003c/td\u003e\n  \t  \u003ctd\u003e 2023 \u003c/td\u003e\n      \u003ctd\u003e2K \u003c/td\u003e\n    \t\u003ctd\u003e72K/72K \u003c/td\u003e\n    \t\u003ctd\u003e Multi-view Image  \u003c/td\u003e\n  \t  \u003ctd\u003e ✗\u003c/td\u003e\n    \t\u003ctd\u003e Lane Centerline, Lane Segment \u003c/td\u003e\n      \u003ctd\u003e  3D  \u003c/td\u003e\n    \t\u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e✓\u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://arxiv.org/abs/2304.10440.pdf\" target=\"_blank\" title=\"Homepage\"\u003eLink\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n\u003c/tr\u003e\n\n\n\u003c/table\u003e\n\n\u003c/details\u003e\n\u003cdetails\u003e\n\u003csummary\u003ePrediction and Planning Datasets\u003c/summary\u003e\n\n\u003ctable\u003e\n\u003ccapital\u003e\u003c/capital\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \u003cth rowspan=1 colspan=1\u003eSubtask\u003c/th\u003e\n    \u003cth rowspan=1 \u003e Input\u003c/th\u003e\n    \u003cth  colspan=1 \u003eOutput\u003c/th\u003e\n    \u003cth  colspan=1 \u003eEvaluation\u003c/th\u003e\n    \u003cth  colspan=1 \u003eDataset\u003c/th\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n  \t  \u003ctd rowspan=9 \u003e Motion Prediction\u003c/td\u003e\n    \t\u003ctd  rowspan=9\u003e Surrounding Traffic States \u003c/td\u003e\n  \t  \u003ctd  rowspan=9 \u003e Spatiotemporal Trajectories of Single/Multiple Vehicle(s) \u003c/td\u003e\n    \t\u003ctd  rowspan=9 \u003e Displacement Error \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.argoverse.org\" target=\"_blank\" \n      title=\"Homepage\"\u003eArgoverse\u003c/a\u003e\u003c/td\u003e \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.nuscenes.org/\" target=\"_blank\" \n      title=\"Homepage\"\u003enuScenes\u003c/a\u003e\u003c/td\u003e  \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n    \t\u003ctd\u003e\u003ca href=\"https://github.com/waymo-research/waymo-open-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eWaymo\u003c/a\u003e\u003c/td\u003e   \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/interaction-dataset/interaction-dataset\" target=\"_blank\" \n      title=\"Homepage\"\u003eInteraction\u003c/a\u003e\u003c/td\u003e  \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://tum-cps.pages.gitlab.lrz.de/mona-dataset/\" target=\"_blank\" \n      title=\"Homepage\"\u003eMONA\u003c/a\u003e\u003c/td\u003e  \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n  \t  \u003ctd rowspan=7 \u003e Trajectory Planning\u003c/td\u003e\n    \t\u003ctd  rowspan=7\u003e Motion States for Ego Vehicles, Scenario Cognition and Prediction \u003c/td\u003e\n  \t  \u003ctd  rowspan=7 \u003e Trajectories for Ego Vehicles \u003c/td\u003e\n    \t\u003ctd  rowspan=7 \u003e Displacement Error, Safety, Compliance, Comfort \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://www.nuscenes.org/nuplan\" target=\"_blank\" \n      title=\"Homepage\"\u003enuPlan \u003c/a\u003e\u003c/td\u003e  \t \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://carlachallenge.org/\" target=\"_blank\" \n      title=\"Homepage\"\u003e CARLA \u003c/a\u003e\u003c/td\u003e \n\u003c/tr\u003e   \n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/metadriverse/metadrive\" target=\"_blank\" title=\"Homepage\"\u003eMetaDrive\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/ApolloScapeAuto/dataset-api\" target=\"_blank\" title=\"Homepage\"\u003eApollo\u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003ctr align=\"middle\"\u003e\n  \t  \u003ctd rowspan=9 \u003e Path Planning\u003c/td\u003e\n    \t\u003ctd  rowspan=9\u003e Maps for Road Network\u003c/td\u003e\n  \t  \u003ctd  rowspan=9 \u003e Routes Connecting to Nodes and Links \u003c/td\u003e\n    \t\u003ctd  rowspan=9 \u003e Efficiency, Energy Conservation \u003c/td\u003e\n      \u003ctd\u003e\u003ca href=\"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\u0026arnumber=4653466\" target=\"_blank\" \n      title=\"Homepage\"\u003eOpenStreetMap \u003c/a\u003e\u003c/td\u003e \n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n      \u003ctd\u003e\u003ca href=\"https://github.com/bstabler/TransportationNetworks\" target=\"_blank\" \n      title=\"Homepage\"\u003eTransportation Networks \u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e  \n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003e\u003ca href=\"https://github.com/asu-trans-ai-lab/DTALite\" target=\"_blank\" \n      title=\"Homepage\"\u003e DTAlite \u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e\n       \u003ctd\u003e\u003ca href=\"https://dot.ca.gov/programs/traffic-operations/mpr/pems-source\" target=\"_blank\" \n      title=\"Homepage\"\u003ePeMS  \u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \u003c/tr\u003e\n\u003ctr align=\"middle\"\u003e \n      \u003ctd\u003e\u003ca href=\"https://github.com/toddwschneider/nyc-taxi-data\" target=\"_blank\" \n      title=\"Homepage\"\u003eNew York City Taxi Data  \u003c/a\u003e\u003c/td\u003e\n\u003c/tr\u003e\n\n\u003c/table\u003e\n\u003c/details\u003e\n\u003c/details\u003e\n\n\n\n## OpenScene\n\u003cdetails\u003e\n\nThe Largest up-to-date **3D Occupancy Forecasting** dataset for visual pre-training.\n\n**Quick facts:**\n- Task: given the large amount of data, predict the 3D occupancy in the environment. \n- Origin dataset: `nuPlan`\n- Repo: https://github.com/OpenDriveLab/OpenScene\n- Related work: [OccNet](https://github.com/OpenDriveLab/OccNet)\n- Related challenge: [3D Occupancy Prediction Challenge 2023](https://opendrivelab.com/AD23Challenge.html#Track3), [Occupancy and Flow AGC Challenge 2024](https://opendrivelab.com/challenge2024/#occupancy_and_flow), [Predictive World Model AGC Challenge 2024](https://opendrivelab.com/challenge2024/#predictive_world_model)\n\u003c/details\u003e\n\n## OpenLane-V2 Update\n\u003cdetails\u003e\n\nFlourishing [OpenLane-V2](https://github.com/OpenDriveLab/OpenLane-V2) with **Standard Definition (SD) Map and Map Elements**.\n\n**Quick facts:**\n- Task: given multi-view images and SD-map (also known as ADAS map) as input, build the driving scene on the fly _without_ the aid of HD-map. \n- Repo: https://github.com/OpenDriveLab/OpenLane-V2\n- Related work: [OpenLane-V2](https://openreview.net/forum?id=OMOOO3ls6g), [TopoNet](https://github.com/OpenDriveLab/TopoNet), [LaneSegNet](https://github.com/OpenDriveLab/LaneSegNet)\n- Related challenge: [Lane Topology Challenge 2023](https://opendrivelab.com/AD23Challenge.html#openlane_topology), [Mapless Driving AGC Challenge 2024](https://opendrivelab.com/challenge2024/#mapless_driving)\n\u003c/details\u003e\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenDriveLab%2FDriveAGI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOpenDriveLab%2FDriveAGI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOpenDriveLab%2FDriveAGI/lists"}