mlsanityData to 14 Oct 2026

A Vision-Centric Approach for Static Map Element Annotation

arXiv 2309.11754 ↗First posted 21 Sep 2023cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

The recent development of online static map element (a.k.a. HD Map) construction algorithms has raised a vast demand for data with ground truth annotations. However, available public datasets currently cannot provide high-quality training data regarding consistency and accuracy. To this end, we present CAMA: a vision-centric approach for Consistent and Accurate Map Annotation. Without LiDAR inputs, our proposed framework can still generate high-quality 3D annotations of static map elements. Specifically, the annotation can achieve high reprojection accuracy across all surrounding cameras and is spatial-temporal consistent across the whole sequence. We apply our proposed framework to the popular nuScenes dataset to provide efficient and highly accurate annotations. Compared with the original nuScenes static map element, models trained with annotations from CAMA achieve lower reprojection errors (e.g., 4.73 vs. 8.03 pixels).

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 21 Sep 2023.

Builds on

33 of 46 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2023Segment Anythingcited by 8,234
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,044
  8. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 732
  9. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  10. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  11. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 341
  12. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 328
21 more
  1. 2022MapTR: Structured Modeling and Learning for Online Vectorized HD Map Constructioncited by 314
  2. 2021HDMapNet: An Online HD Map Construction and Evaluation Frameworkcited by 281
  3. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  4. 2022VectorMapNet: End-to-end Vectorized HD Map Learningcited by 245
  5. 2023MapTRv2: An End-to-End Framework for Online Vectorized HD Map Constructioncited by 193
  6. 2022PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmarkcited by 140
  7. 2022Vision-Centric BEV Perception: A Surveycited by 126
  8. 20183D-LaneNet: End-to-End 3D Multiple Lane Detectioncited by 107
  9. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 90
  10. 2022Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformercited by 80
  11. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  12. 2020A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye Viewcited by 72
  13. 2023Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Constructioncited by 50
  14. 2022ONCE-3DLanes: Building Monocular 3D Lane Detectioncited by 44
  15. 2017Dirty Pixels: Towards End-to-End Image Processing and Perceptioncited by 42
  16. 2021RoadMap: A Light-Weight Semantic Map for Visual Localization towards Autonomous Drivingcited by 34
  17. 2022MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbonescited by 29
  18. 2023RoMe: Towards Large Scale Road Surface Reconstruction via Mesh Representationcited by 20
  19. 2023VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scenecited by 10
  20. 2021Deep Online Correction for Monocular Visual Odometrycited by 9
  21. 2022Towards Accurate Ground Plane Normal Estimation from Ego-Motioncited by 2

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 4.

7 papers.

  1. 2025Learning-based 3D Reconstruction in Autonomous Driving: A Comprehensive Surveycited by 9
  2. 2024PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentationcited by 5
  3. 2025PseudoMapTrainer: Learning Online Mapping without HD Mapscited by 5
  4. 2024CAMAv2: A Vision-Centric Approach for Static Map Element Annotationcited by 3
  5. 2025Iterative Volume Fusion for Asymmetric Stereo Matchingcited by 1
  6. 2024VRSO: Visual-Centric Reconstruction for Static Object Annotationcited by 0
  7. 2025MRASfM: Multi-Camera Reconstruction and Aggregation through Structure-from-Motion in Driving Scenescited by 0