mlsanityData to 7 Oct 2026

Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes

arXiv 2208.08621 ↗First posted 18 Aug 2022cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introduce a simple, efficient, and effective two-stage detector, termed as Ret3D. At the core of Ret3D is the utilization of novel intra-frame and inter-frame relation modules to capture the spatial and temporal relations accordingly. More Specifically, intra-frame relation module (IntraRM) encapsulates the intra-frame objects into a sparse graph and thus allows us to refine the object features through efficient message passing. On the other hand, inter-frame relation module (InterRM) densely connects each object in its corresponding tracked sequences dynamically, and leverages such temporal information to further enhance its representations efficiently through a lightweight transformer network. We instantiate our novel designs of IntraRM and InterRM with general center-based or anchor-based detectors and evaluate them on Waymo Open Dataset (WOD). With negligible extra overhead, Ret3D achieves the state-of-the-art performance, being 5.5% and 3.2% higher than the recent competitor in terms of the LEVEL 1 and LEVEL 2 mAPH metrics on vehicle detection, respectively.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 50 of its 62 references that are in the map. First posted on arXiv 18 Aug 2022.

Builds on

50 of 62 references.

References · 50

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  6. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  10. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  11. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  12. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
38 more
  1. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  3. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  4. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  6. 2020Pre-Trained Image Processing Transformercited by 891
  7. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  8. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  9. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  10. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  11. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  12. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  13. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  14. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  15. 2017Relation Networks for Object Detectioncited by 305
  16. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  17. 2021Voxel Transformer for 3D Object Detectioncited by 247
  18. 2019Disentangling Monocular 3D Object Detectioncited by 215
  19. 2021Group-Free 3D Object Detection via Transformerscited by 215
  20. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  21. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  22. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  23. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  24. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 144
  25. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  26. 2020Pillar-based Object Detection for Autonomous Drivingcited by 137
  27. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  28. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  29. 2019Fast Point R-CNNcited by 119
  30. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  31. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  32. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  33. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  34. 2016Vote3Deep: Fast Object Detection in 3D Point Clouds Using Efficient Convolutional Neural Networkscited by 72
  35. 2021Object DGCNN: 3D Object Detection using Dynamic Graphscited by 58
  36. 2019Relation Graph Network for 3D Object Detection in Point Cloudscited by 27
  37. 2020DOPS: Learning to Detect 3D Objects and Predict their 3D Shapescited by 27
  38. 2020SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Cloudscited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 1; 2025: 4; 2026: 2.

8 papers.

  1. 2024GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphscited by 3
  2. 2023GACE: Geometry Aware Confidence Enhancement for Black-Box 3D Object Detectors on LiDAR-Datacited by 2
  3. 2025Deeply Dual Supervised learning for melanoma recognitioncited by 0
  4. 2025Edge Detection for Organ Boundaries via Top Down Refinement and SubPixel Upsamplingcited by 0
  5. 2025DualResolution Residual Architecture with Artifact Suppression for Melanocytic Lesion Segmentationcited by 0
  6. 2025VesselRW: Weakly Supervised Subcutaneous Vessel Segmentation via Learned Random Walk Propagationcited by 0
  7. 2026WaDi: Weight Direction-aware Distillation for One-step Image Synthesiscited by 0
  8. 2026RoadGIE: Towards A Global-Scale Aerial Benchmark for Generalizable Interactive Road Extractioncited by 0