mlsanityData to 7 Oct 2026

Improving Distant 3D Object Detection Using 2D Box Supervision

arXiv 2403.09230 ↗First posted 14 Mar 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Improving the detection of distant 3d objects is an important yet challenging task. For camera-based 3D perception, the annotation of 3d bounding relies heavily on LiDAR for accurate depth information. As such, the distance of annotation is often limited due to the sparsity of LiDAR points on distant objects, which hampers the capability of existing detectors for long-range scenarios. We address this challenge by considering only 2D box supervision for distant objects since they are easy to annotate. We propose LR3D, a framework that learns to recover the missing depth of distant objects. LR3D adopts an implicit projection head to learn the generation of mapping between 2D boxes and depth using the 3D supervision on close objects. This mapping allows the depth estimation of distant objects conditioned on their 2D boxes, making long-range 3D detection with 2D supervision feasible. Experiments show that without distant 3D annotations, LR3D allows camera-based methods to detect distant objects (over 200m) with comparable accuracy to full 3D supervision. Our framework is general, and could widely benefit 3D detection methods to a large extent.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 58 of its 70 references that are in the map. First posted on arXiv 14 Mar 2024.

Builds on

58 of 70 references.

References · 58

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015Fast R-CNNcited by 2,930
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2020Point Transformercited by 1,462
  11. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  12. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
38 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  2. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  3. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  9. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  10. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  11. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  12. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  13. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  14. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  15. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  16. 2022BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervisioncited by 302
  17. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  18. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  19. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  20. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  21. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 184
  22. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  23. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  24. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  25. 2019Point-Based Multi-View Stereo Networkcited by 147
  26. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  27. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  28. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  29. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  30. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  31. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  32. 20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
  33. 2015Sparse 3D convolutional neural networkscited by 71
  34. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  35. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  36. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  37. 2020Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detectioncited by 39
  38. 2021To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernelscited by 39

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2026SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detectioncited by 1
  2. 2025LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoringcited by 0
  3. 2025Rethink 3D Object Detection from Physical Worldcited by 0
  4. 2026SimPB++: Simultaneously Detecting 2D and 3D Objects from Multiple Camerascited by 0
  5. 2026Horizon3D: Sparse Radar-Camera Fusion for Long-Range 3D Perception in Autonomous Drivingcited by 0
  6. 2026RAF: Reliability-Aware Fusion of Camera, LiDAR, and 4D RADAR for Robust 3D Object Detection in Adverse Weathercited by 0