mlsanityData to 14 Oct 2026

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

arXiv 1812.07179 ↗First posted 18 Dec 2018cs.CVcited by 457

Not on the map. Why?

Abstract (arXiv)

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper monocular or stereo imagery data have, until now, resulted in drastically lower accuracies --- a gap that is commonly attributed to poor image-based depth estimation. However, in this paper we argue that it is not the quality of the data but its representation that accounts for the majority of the difference. Taking the inner workings of convolutional neural networks into consideration, we propose to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal. With this representation we can apply different existing LiDAR-based detection algorithms. On the popular KITTI benchmark, our approach achieves impressive improvements over the existing state-of-the-art in image-based performance --- raising the detection accuracy of objects within the 30m range from the previous state-of-the-art of 22% to an unprecedented 74%. At the time of submission our algorithm holds the highest entry on the KITTI 3D object detection leaderboard for stereo-image-based approaches. Our code is publicly available at https://github.com/mileyan/pseudo_lidar.

Key facts. Cited by 457 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 105; 2022: 114; 2023: 90; 2024: 75; 2025: 47; 2026: 26.

457 papers.

Sort:

By area:

  1. 2024Depth Anything V2cited by 1,422
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  3. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  5. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  6. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  7. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  8. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  9. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 316
  10. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  11. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  12. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
38 more
  1. 2021FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Camerascited by 239
  2. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  3. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  4. 2021ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrationscited by 197
  5. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  6. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  7. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  8. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  9. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  10. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
  11. 2021Multimodal Virtual Point 3D Detectioncited by 166
  12. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
  13. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 160
  14. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  15. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 156
  16. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  17. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  18. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 140
  19. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  20. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  21. 2022Vision-Centric BEV Perception: A Surveycited by 126
  22. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  23. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  24. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
  25. 2023Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Drivingcited by 114
  26. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 109
  27. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  28. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  29. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  30. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  31. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 86
  32. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  33. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84
  34. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  35. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  36. 2021Monocular Quasi-Dense 3D Object Trackingcited by 81
  37. 2022Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Taskcited by 81
  38. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80

50 most cited of 457 All 457 (JSON)