mlsanityData to 7 Oct 2026

Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds

arXiv 2207.01030 ↗First posted 3 Jul 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

To boost a detector for single-frame 3D object detection, we present a new approach to train it to simulate features and responses following a detector trained on multi-frame point clouds. Our approach needs multi-frame point clouds only when training the single-frame detector, and once trained, it can detect objects with only single-frame point clouds as inputs during the inference. We design a novel Simulated Multi-Frame Single-Stage object Detector (SMF-SSD) framework to realize the approach: multi-view dense object fusion to densify ground-truth objects to generate a multi-frame point cloud; self-attention voxel distillation to facilitate one-to-many knowledge transfer from multi- to single-frame voxels; multi-scale BEV feature distillation to transfer knowledge in low-level spatial and high-level semantic BEV features; and adaptive response distillation to activate single-frame responses of high confidence and accurate localization. Experimental results on the Waymo test set show that our SMF-SSD consistently outperforms all state-of-the-art single-frame 3D object detectors for all object classes of difficulty levels 1 and 2 in terms of both mAP and mAPH.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 57 of its 62 references that are in the map. First posted on arXiv 3 Jul 2022.

Builds on

57 of 62 references.

References · 57

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  11. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  12. 2019Similarity-Preserving Knowledge Distillationcited by 507
38 more
  1. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  2. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  3. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  4. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  5. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  6. 2021Distilling Knowledge via Knowledge Reviewcited by 285
  7. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  8. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  9. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  10. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 188
  11. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  12. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  13. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  14. 2020CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detectioncited by 159
  15. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  16. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  17. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  18. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  19. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  20. 2021General Instance Distillation for Object Detectioncited by 113
  21. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  22. 2021Distilling Object Detectors via Decoupled Featurescited by 105
  23. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  24. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  25. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  26. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 83
  27. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  28. 2021M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformerscited by 74
  29. 20213D-MAN: 3D Multi-frame Attention Network for Object Detectioncited by 73
  30. 2020A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detectioncited by 70
  31. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  32. 2021Object DGCNN: 3D Object Detection using Dynamic Graphscited by 58
  33. 2019StarNet: Targeted Computation for Object Detection in Point Cloudscited by 46
  34. 2019Distant Vehicle Detection Using Radar and Visioncited by 44
  35. 2021Instance-Conditional Knowledge Distillation for Object Detectioncited by 42
  36. 2020Improving 3D Object Detection through Progressive Population Based Augmentationcited by 41
  37. 2021M3DSSD: Monocular 3D Single Stage Object Detectorcited by 39
  38. 2020Distilling Object Detectors with Task Adaptive Regularizationcited by 36

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 0; 2026: 1.

6 papers.

  1. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  2. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  3. 2024TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentationcited by 13
  4. 2024Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detectioncited by 11
  5. 2024LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Drivingcited by 8
  6. 2026C2E: Boosting Ego-Only 3D Object Detection via Multi-Teacher Contrastive Knowledge Distillationcited by 1