mlsanityData to 14 Oct 2026

Object DGCNN: 3D Object Detection using Dynamic Graphs

arXiv 2110.06923 ↗First posted 13 Oct 2021cs.CV cs.AI cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

3D object detection often involves complicated training and testing pipelines, which require substantial domain knowledge about individual datasets. Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D object detection architecture on point clouds. Our method models 3D object detection as message passing on a dynamic graph, generalizing the DGCNN framework to predict a set of objects. In our construction, we remove the necessity of post-processing via object confidence aggregation or non-maximum suppression. To facilitate object detection from sparse point clouds, we also propose a set-to-set distillation approach customized to 3D detection. This approach aligns the outputs of the teacher model and the student model in a permutation-invariant fashion, significantly simplifying knowledge distillation for the 3D detection task. Our method achieves state-of-the-art performance on autonomous driving benchmarks. We also provide abundant analysis of the detection model and distillation framework.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 57 of its 81 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

57 of 81 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2020End-to-End Object Detection with Transformerscited by 7,414
  8. 2017Mask R-CNNcited by 7,277
  9. 2016Layer Normalizationcited by 5,669
  10. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  11. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  12. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
38 more
  1. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  3. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  4. 2014FitNets: Hints for Thin Deep Netscited by 1,653
  5. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2019Contrastive Multiview Codingcited by 1,301
  8. 2019Objects as Pointscited by 1,175
  9. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  10. 2016Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfercited by 1,077
  11. 2020Designing Network Design Spacescited by 960
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  13. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  14. 2019Relational Knowledge Distillationcited by 889
  15. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  16. 2017Focal Loss for Dense Object Detectioncited by 752
  17. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  18. 2019Contrastive Representation Distillationcited by 748
  19. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  20. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  21. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  22. 2015Cyclical Learning Rates for Training Neural Networkscited by 629
  23. 2018Born Again Neural Networkscited by 546
  24. 2019Similarity-Preserving Knowledge Distillationcited by 516
  25. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  26. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 326
  27. 2020Deep Continuous Fusion for Multi-Sensor 3D Object Detectioncited by 263
  28. 2015Unifying distillation and privileged informationcited by 233
  29. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  30. 2019Distilling Object Detectors with Fine-grained Feature Imitationcited by 189
  31. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  32. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  33. 2015End-to-end people detection in crowded scenescited by 140
  34. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  35. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  36. 2020ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votescited by 119
  37. 2019BAM! Born-Again Multi-Task Networks for Natural Language Understandingcited by 85
  38. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 24; 2023: 16; 2024: 14; 2025: 3; 2026: 1.

58 papers.

Sort:

By area:

  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  2. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  3. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 332
  4. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  5. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  6. 2022DeepInteraction: 3D Object Detection via Modality Interactioncited by 125
  7. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  8. 2022LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perceptioncited by 74
  9. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 73
  10. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 72
  11. 2022AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detectioncited by 70
  12. 2022BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detectioncited by 66
38 more
  1. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  2. 2022A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspectivecited by 56
  3. 2022AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detectioncited by 46
  4. 2022Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detectioncited by 46
  5. 2022Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graphcited by 42
  6. 2023DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillationcited by 41
  7. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  8. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  9. 2022Towards Efficient 3D Object Detection with Knowledge Distillationcited by 29
  10. 2023UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalitiescited by 29
  11. 2023Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detectioncited by 28
  12. 2024CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillationcited by 28
  13. 2022Imperceptible and Robust Backdoor Attack in 3D Point Cloudcited by 25
  14. 2024GraphAD: Interaction Scene Graph for End-to-end Autonomous Drivingcited by 25
  15. 2023Deep Graph Reprogrammingcited by 22
  16. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  17. 2022Point2Seq: Detecting 3D Objects as Sequencescited by 15
  18. 2024DeepInteraction++: Multi-Modality Interaction for Autonomous Drivingcited by 15
  19. 2022itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detectioncited by 14
  20. 2024Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encodercited by 14
  21. 2022Li3DeTr: A LiDAR based 3D Detection Transformercited by 11
  22. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  23. 2023TransCAR: Transformer-based Camera-And-Radar Fusion for 3D Object Detectioncited by 11
  24. 2024LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detectioncited by 9
  25. 2022Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenescited by 8
  26. 2023DualCross: Cross-Modality Cross-Domain Adaptation for Monocular BEV Perceptioncited by 8
  27. 2022Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Cloudscited by 6
  28. 2023CurveCloudNet: Processing Point Clouds with 1D Structurecited by 5
  29. 2022MSF3DDETR: Multi-Sensor Fusion 3D Detection Transformer for Autonomous Drivingcited by 3
  30. 2023Link Prediction for Flow-Driven Spatial Networkscited by 3
  31. 2023BEVTrack: A Simple and Strong Baseline for 3D Single Object Tracking in Bird's-Eye Viewcited by 3
  32. 2024Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detectioncited by 3
  33. 2024GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphscited by 3
  34. 2024Scalable Event Cloud Network for Event-based Classificationcited by 3
  35. 2023GLiDR: Topologically Regularized Graph Generative Network for Sparse LiDAR Point Cloudscited by 2
  36. 2024PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysiscited by 2
  37. 2023ShaSTA-Fuse: Camera-LiDAR Sensor Fusion to Model Shape and Spatio-Temporal Affinities for 3D Multi-Object Trackingcited by 1
  38. 2024Graph Neural Networks in Intelligent Transportation Systems: Advances, Applications and Trendscited by 1

50 most cited of 58 All 58 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection
  2. 2025Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features
  3. 2022Semi-supervised 3D Object Detection via Temporal Graph Neural Networks
  4. 2023Representation Disparity-aware Distillation for 3D Object Detection
  5. 2022BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection
  6. 2021Dynamic Knowledge Distillation With Noise Elimination for RGB-D Salient Object Detection
  7. 2021DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization
  8. 2022Prediction-Guided Distillation for Dense Object Detection