mlsanityData to 7 Oct 2026

3D-MAN: 3D Multi-frame Attention Network for Object Detection

arXiv 2103.16054 ↗First posted 30 Mar 2021cs.CVcited by 73

Not on the map. Why?

Abstract (arXiv)

3D object detection is an important module in autonomous driving and robotics. However, many existing methods focus on using single frames to perform 3D detection, and do not fully utilize information from multiple frames. In this paper, we present 3D-MAN: a 3D multi-frame attention network that effectively aggregates features from multiple perspectives and achieves state-of-the-art performance on Waymo Open Dataset. 3D-MAN first uses a novel fast single-frame detector to produce box proposals. The box proposals and their corresponding feature maps are then stored in a memory bank. We design a multi-view alignment and aggregation module, using attention networks, to extract and aggregate the temporal features stored in the memory bank. This effectively combines the features coming from different perspectives of the scene. We demonstrate the effectiveness of our approach on the large-scale complex Waymo Open Dataset, achieving state-of-the-art results compared to published single-frame and multi-frame methods.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 31 of its 38 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

31 of 38 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  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. 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. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2019Objects as Pointscited by 1,172
  10. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  11. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  12. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
19 more
  1. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  2. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  3. 2017Relation Networks for Object Detectioncited by 305
  4. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  5. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  6. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  7. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  8. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  9. 2015End-to-end people detection in crowded scenescited by 140
  10. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  11. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  12. 2019Sequence Level Semantics Aggregation for Video Object Detectioncited by 87
  13. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  14. 2019Relation Distillation Networks for Video Object Detectioncited by 77
  15. 2020LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attentioncited by 65
  16. 2020AFDet: Anchor Free One Stage 3D Object Detectioncited by 63
  17. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  18. 2019StarNet: Targeted Computation for Object Detection in Point Cloudscited by 46
  19. 2020An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Cloudscited by 45

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 19; 2023: 30; 2024: 14; 2025: 6; 2026: 1.

73 papers.

Sort:

By area:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 313
  3. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  4. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  5. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2022PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detectioncited by 99
  8. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  9. 2023Visual Point Cloud Forecasting enables Scalable Autonomous Drivingcited by 97
  10. 2021AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Cloudscited by 88
  11. 2022Fully Sparse 3D Object Detectioncited by 84
  12. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
38 more
  1. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  2. 2022MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detectioncited by 65
  3. 2023Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perceptioncited by 65
  4. 2023Fully Sparse 3D Occupancy Predictioncited by 61
  5. 2022GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Cloudscited by 57
  6. 2022Dynamic 3D Scene Analysis by Point Cloud Accumulationcited by 47
  7. 2023FastPillars: A Deployment-friendly Pillar-based 3D Detectorcited by 39
  8. 2022A Unified Query-based Paradigm for Point Cloud Understandingcited by 32
  9. 2023Super Sparse 3D Object Detectioncited by 32
  10. 2023BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregationcited by 31
  11. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  12. 2023Fully Sparse Fusion for 3D Object Detectioncited by 29
  13. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  14. 2022Densely Constrained Depth Estimator for Monocular 3D Object Detectioncited by 27
  15. 2021From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detectioncited by 24
  16. 2023PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformercited by 21
  17. 2024SEED: A Simple and Effective 3D DETR in Point Cloudscited by 19
  18. 2024CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detectioncited by 18
  19. 2024HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Camerascited by 16
  20. 2022MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detectioncited by 15
  21. 2023MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequencescited by 15
  22. 2025TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perceptioncited by 15
  23. 2022INT: Towards Infinite-frames 3D Detection with An Efficient Frameworkcited by 14
  24. 2022Sparse2Dense: Learning to Densify 3D Features for 3D Object Detectioncited by 14
  25. 2023MS3D++: Ensemble of Experts for Multi-Source Unsupervised Domain Adaptation in 3D Object Detectioncited by 14
  26. 2023MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequencescited by 13
  27. 2023MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detectioncited by 12
  28. 2023LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perceptioncited by 11
  29. 2023T-MAE: Temporal Masked Autoencoders for Point Cloud Representation Learningcited by 11
  30. 2024ScatterFormer: Efficient Voxel Transformer with Scattered Linear Attentioncited by 11
  31. 2022A Survey of Robust 3D Object Detection Methods in Point Cloudscited by 10
  32. 2023Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detectioncited by 8
  33. 2023PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detectioncited by 8
  34. 2024SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labellingcited by 8
  35. 2022Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Cloudscited by 6
  36. 2022TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detectioncited by 6
  37. 2023Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detectioncited by 6
  38. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6

50 most cited of 73 All 73 (JSON)