mlsanityData to 14 Oct 2026

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

arXiv 2304.10440 ↗First posted 20 Apr 2023cs.CVcited by 83

Not on the map. Why?

Abstract (arXiv)

Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments. However, existing benchmarks tend to oversimplify the scene by solely focusing on lane perception tasks. Observing that human drivers rely on both lanes and traffic signals to operate their vehicles safely, we present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure. The objective of the presented dataset is to advance research in understanding the structure of road scenes by examining the relationship between perceived entities, such as traffic elements and lanes. Leveraging existing datasets, OpenLane-V2 consists of 2,000 annotated road scenes that describe traffic elements and their correlation to the lanes. It comprises three primary sub-tasks, including the 3D lane detection inherited from OpenLane, accompanied by corresponding metrics to evaluate the model's performance. We evaluate various state-of-the-art methods, and present their quantitative and qualitative results on OpenLane-V2 to indicate future avenues for investigating topology reasoning in traffic scenes.

Key facts. Cited by 83 papers in the map (data through 14 Oct 2026). Builds on 25 of its 47 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

25 of 47 references.

References · 25

  1. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  4. 2018Datasheets for Datasetscited by 1,386
  5. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  6. 2022Planning-oriented Autonomous Drivingcited by 1,087
  7. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  8. 2016Visual Relationship Detection with Language Priorscited by 334
  9. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 314
  10. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 245
  11. 2017Learning to Detect Human-Object Interactionscited by 240
  12. 2015Visual Semantic Role Labelingcited by 190
13 more
  1. 2018The ApolloScape Open Dataset for Autonomous Driving and its Applicationcited by 190
  2. 2017Spatial As Deep: Spatial CNN for Traffic Scene Understandingcited by 187
  3. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  4. 2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102
  5. 2021Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Imagescited by 98
  6. 2020CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blendingcited by 80
  7. 2017VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognitioncited by 56
  8. 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54
  9. 2023Graph-based Topology Reasoning for Driving Scenescited by 54
  10. 2019The Mapillary Traffic Sign Dataset for Detection and Classification on a Global Scalecited by 50
  11. 2022ONCE-3DLanes: Building Monocular 3D Lane Detectioncited by 44
  12. 2014Real time Detection of Lane Markers in Urban Streetscited by 41
  13. 2020Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehiclescited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 25; 2025: 28; 2026: 23.

83 papers.

Sort:

By area:

  1. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 536
  2. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  3. 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoningcited by 143
  4. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 99
  5. 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
  6. 2023Fully Sparse 3D Occupancy Predictioncited by 64
  7. 2024Embodied Understanding of Driving Scenarioscited by 63
  8. 2024P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priorscited by 54
  9. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  10. 2024TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenescited by 29
  11. 2024Enhancing Vectorized Map Perception with Historical Rasterized Mapscited by 29
  12. 2023Open-sourced Data Ecosystem in Autonomous Driving: the Present and Futurecited by 23
38 more
  1. 2024Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priorscited by 21
  2. 2024Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?cited by 20
  3. 2025Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Drivingcited by 19
  4. 2024RoadPainter: Points Are Ideal Navigators for Topology transformERcited by 17
  5. 2025Chameleon: Fast-slow Neuro-symbolic Lane Topology Extractioncited by 16
  6. 2024SemVecNet: Generalizable Vector Map Generation for Arbitrary Sensor Configurationscited by 12
  7. 2025SMART: Advancing Scalable Map Priors for Driving Topology Reasoningcited by 12
  8. 2023GroupLane: End-to-End 3D Lane Detection with Channel-wise Groupingcited by 11
  9. 2024Driving by the Rules: A Benchmark for Integrating Traffic Sign Regulations into Vectorized HD Mapcited by 11
  10. 2025SeqGrowGraph: Learning Lane Topology as a Chain of Graph Expansionscited by 10
  11. 2024XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesiscited by 9
  12. 2025SEPT: Standard-Definition Map Enhanced Scene Perception and Topology Reasoning for Autonomous Drivingcited by 9
  13. 2025TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Drivingcited by 9
  14. 2025Reusing Attention for One-stage Lane Topology Understandingcited by 9
  15. 2024Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regressioncited by 8
  16. 2024TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problemcited by 7
  17. 2025Tracking Meets Large Multimodal Models for Driving Scenario Understandingcited by 7
  18. 2023Mind the map! Accounting for existing map information when estimating online HDMaps from sensorcited by 6
  19. 2025Persistent Autoregressive Mapping with Traffic Rules for Autonomous Drivingcited by 6
  20. 2025LaneDiffusion: Improving Centerline Graph Learning via Prior Injected BEV Feature Generationcited by 6
  21. 2024Continuity Preserving Online CenterLine Graph Learningcited by 5
  22. 2024Enhancing Lane Segment Perception and Topology Reasoning with Crowdsourcing Trajectory Priorscited by 5
  23. 2024TopoBDA: Towards Bezier Deformable Attention for Road Topology Understandingcited by 5
  24. 2024LGmap: Local-to-Global Mapping Network for Online Long-Range Vectorized HD Map Constructioncited by 4
  25. 2024Monocular Lane Detection Based on Deep Learning: A Surveycited by 4
  26. 2024ExelMap: Explainable Element-based HD-Map Change Detection and Updatecited by 3
  27. 2024M3TR: A Generalist Model for Real-World HD Map Completioncited by 3
  28. 2025MapGS: Generalizable Pretraining and Data Augmentation for Online Mapping via Novel View Synthesiscited by 3
  29. 2025Geometry-Guided Representations for Coherent Lane and Traffic Topology Reasoning in Driving Scenescited by 3
  30. 2025TopoStreamer: Temporal Lane Segment Topology Reasoning in Autonomous Drivingcited by 3
  31. 2025Coherent Online Road Topology Estimation and Reasoning with Standard-Definition Mapscited by 3
  32. 2025FASTopoWM: Fast-Slow Lane Segment Topology Reasoning with Latent World Modelscited by 3
  33. 2025RATopo: Improving Lane Topology Reasoning via Redundancy Assignmentcited by 3
  34. 2026OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Modelscited by 3
  35. 2024Generation of Training Data from HD Maps in the Lanelet2 Frameworkcited by 2
  36. 2025TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videoscited by 2
  37. 2025A Concise Survey on Lane Topology Reasoning for HD Mappingcited by 2
  38. 2025Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Drivingcited by 2

50 most cited of 83 All 83 (JSON)