mlsanityData to 14 Oct 2026

PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction

arXiv 2308.16477 ↗First posted 31 Aug 2023cs.CVcited by 85

Not on the map. Why?

Abstract (arXiv)

Vectorized high-definition map online construction has garnered considerable attention in the field of autonomous driving research. Most existing approaches model changeable map elements using a fixed number of points, or predict local maps in a two-stage autoregressive manner, which may miss essential details and lead to error accumulation. Towards precise map element learning, we propose a simple yet effective architecture named PivotNet, which adopts unified pivot-based map representations and is formulated as a direct set prediction paradigm. Concretely, we first propose a novel point-to-line mask module to encode both the subordinate and geometrical point-line priors in the network. Then, a well-designed pivot dynamic matching module is proposed to model the topology in dynamic point sequences by introducing the concept of sequence matching. Furthermore, to supervise the position and topology of the vectorized point predictions, we propose a dynamic vectorized sequence loss. Extensive experiments and ablations show that PivotNet is remarkably superior to other SOTAs by 5.9 mAP at least. The code will be available soon.

Key facts. Cited by 85 papers in the map (data through 14 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 31 Aug 2023.

Builds on

30 of 44 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020End-to-End Object Detection with Transformerscited by 7,414
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  6. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  7. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  8. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  10. 2019On the Convergence of Adam and Beyondcited by 841
  11. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 713
  12. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
18 more
  1. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  2. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 314
  3. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 281
  4. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 245
  5. 2020LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mappingcited by 188
  6. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 174
  7. 2020ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Networkcited by 170
  8. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  9. 2020Keep your Eyes on the Lane: Real-time Attention-guided Lane Detectioncited by 138
  10. 2020End-to-end Lane Shape Prediction with Transformerscited by 111
  11. 2022Rethinking Efficient Lane Detection via Curve Modelingcited by 88
  12. 2018Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networkscited by 84
  13. 2023End-to-End Vectorized HD-map Construction with Piecewise Bezier Curvecited by 82
  14. 2022A Keypoint-based Global Association Network for Lane Detectioncited by 68
  15. 2021Focus on Local: Detecting Lane Marker from Bottom Up via Key Pointcited by 65
  16. 2021HDMapGen: A Hierarchical Graph Generative Model of High Definition Mapscited by 40
  17. 2019End-to-end Lane Detection through Differentiable Least-Squares Fittingcited by 36
  18. 2021YOLinO: Generic Single Shot Polyline Detection in Real Timecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 35; 2025: 34; 2026: 11.

85 papers.

Sort:

By area:

  1. 2024EMMA: End-to-End Multimodal Model for Autonomous Drivingcited by 231
  2. 2024MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mappingcited by 68
  3. 2023Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Mapscited by 58
  4. 2023LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Drivingcited by 57
  5. 2024P-MapNet: Far-seeing Map Generator Enhanced by both SDMap and HDMap Priorscited by 54
  6. 2024MGMap: Mask-Guided Learning for Online Vectorized HD Map Constructioncited by 52
  7. 2024HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Constructioncited by 48
  8. 2024SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Drivingcited by 47
  9. 2024Leveraging Enhanced Queries of Point Sets for Vectorized Map Constructioncited by 46
  10. 2024Stream Query Denoising for Vectorized HD Map Constructioncited by 43
  11. 2023Online Vectorized HD Map Construction using Geometrycited by 42
  12. 2023TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoningcited by 41
38 more
  1. 2024Producing and Leveraging Online Map Uncertainty in Trajectory Predictioncited by 33
  2. 2024TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenescited by 29
  3. 2024Enhancing Vectorized Map Perception with Historical Rasterized Mapscited by 29
  4. 2024Is Your HD Map Constructor Reliable under Sensor Corruptions?cited by 28
  5. 2024MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillationcited by 26
  6. 2024Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Maskscited by 26
  7. 2024PreSight: Enhancing Autonomous Vehicle Perception with City-Scale NeRF Priorscited by 21
  8. 2024Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priorscited by 21
  9. 2024RoadPainter: Points Are Ideal Navigators for Topology transformERcited by 17
  10. 2024MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expertcited by 17
  11. 2024ADMap: Anti-disturbance framework for reconstructing online vectorized HD mapcited by 14
  12. 2025SafeMap: Robust HD Map Construction from Incomplete Observationscited by 14
  13. 2024PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Constructioncited by 12
  14. 2024Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagationcited by 12
  15. 2024DTCLMapper: Dual Temporal Consistent Learning for Vectorized HD Map Constructioncited by 10
  16. 2024PriorDrive: Enhancing Online HD Mapping with Unified Vector Priorscited by 10
  17. 2024MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Constructioncited by 9
  18. 2024MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Constructioncited by 9
  19. 2025TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Drivingcited by 9
  20. 2025What Really Matters for Robust Multi-Sensor HD Map Construction?cited by 9
  21. 2025HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Trackingcited by 8
  22. 2025InteractionMap: Improving Online Vectorized HDMap Construction with Interactioncited by 8
  23. 2024TopoMaskV2: Enhanced Instance-Mask-Based Formulation for the Road Topology Problemcited by 7
  24. 2025Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mappingcited by 7
  25. 2023Mind the map! Accounting for existing map information when estimating online HDMaps from sensorcited by 6
  26. 2024Improving Hierarchical Representations of Vectorized HD Maps with Perspective Cluescited by 6
  27. 2025AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Constructioncited by 6
  28. 2025Delving into Mapping Uncertainty for Mapless Trajectory Predictioncited by 6
  29. 2025Persistent Autoregressive Mapping with Traffic Rules for Autonomous Drivingcited by 6
  30. 2025DAMap: Distance-aware MapNet for High Quality HD Map Constructioncited by 6
  31. 2024Continuity Preserving Online CenterLine Graph Learningcited by 5
  32. 2024Neural HD Map Generation from Multiple Vectorized Tiles Locally Produced by Autonomous Vehiclescited by 5
  33. 2024TopoBDA: Towards Bezier Deformable Attention for Road Topology Understandingcited by 5
  34. 2025Spatial Retrieval Augmented Autonomous Drivingcited by 5
  35. 2024EAN-MapNet: Efficient Vectorized HD Map Construction with Anchor Neighborhoodscited by 4
  36. 2024GenMapping: Unleashing the Potential of Inverse Perspective Mapping for Robust Online HD Map Constructioncited by 4
  37. 2024Monocular Lane Detection Based on Deep Learning: A Surveycited by 4
  38. 2025Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Constructioncited by 4

50 most cited of 85 All 85 (JSON)