mlsanityData to 14 Oct 2026

Transformation-Equivariant 3D Object Detection for Autonomous Driving

arXiv 2211.11962 ↗First posted 22 Nov 2022cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

3D object detection received increasing attention in autonomous driving recently. Objects in 3D scenes are distributed with diverse orientations. Ordinary detectors do not explicitly model the variations of rotation and reflection transformations. Consequently, large networks and extensive data augmentation are required for robust detection. Recent equivariant networks explicitly model the transformation variations by applying shared networks on multiple transformed point clouds, showing great potential in object geometry modeling. However, it is difficult to apply such networks to 3D object detection in autonomous driving due to its large computation cost and slow reasoning speed. In this work, we present TED, an efficient Transformation-Equivariant 3D Detector to overcome the computation cost and speed issues. TED first applies a sparse convolution backbone to extract multi-channel transformation-equivariant voxel features; and then aligns and aggregates these equivariant features into lightweight and compact representations for high-performance 3D object detection. On the highly competitive KITTI 3D car detection leaderboard, TED ranked 1st among all submissions with competitive efficiency.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 37 of its 44 references that are in the map. First posted on arXiv 22 Nov 2022.

Builds on

37 of 44 references.

References · 37

  1. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  2. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  3. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  4. 2016Group Equivariant Convolutional Networkscited by 1,165
  5. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 941
  6. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  9. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  10. 2018Spherical CNNscited by 456
  11. 2019General E(2)-Equivariant Steerable CNNscited by 446
  12. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
25 more
  1. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 410
  2. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
  3. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  4. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  5. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  6. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  7. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 203
  8. 2017Learning Steerable Filters for Rotation Equivariant CNNscited by 194
  9. 2021Multimodal Virtual Point 3D Detectioncited by 166
  10. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  11. 2021PENet: Towards Precise and Efficient Image Guided Depth Completioncited by 146
  12. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  13. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  14. 2020Better Aggregation in Test-Time Augmentationcited by 122
  15. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  16. 2021Improving 3D Object Detection with Channel-wise Transformercited by 108
  17. 2022Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completioncited by 82
  18. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  19. 2016TI-POOLING: transformation-invariant pooling for feature learning in Convolutional Neural Networkscited by 67
  20. 2021Behind the Curtain: Learning Occluded Shapes for 3D Object Detectioncited by 58
  21. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  22. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  23. 2018BirdNet: a 3D Object Detection Framework from LiDAR informationcited by 33
  24. 2022Rotationally Equivariant 3D Object Detectioncited by 21
  25. 2021Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Spacecited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 24; 2025: 15; 2026: 5.

52 papers.

Sort:

By area:

  1. 2023Equivariant Adaptation of Large Pretrained Modelscited by 41
  2. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 36
  3. 20234D Panoptic Segmentation as Invariant and Equivariant Field Predictioncited by 19
  4. 2024DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detectioncited by 19
  5. 2024Neural Radiance Field in Autonomous Driving: A Surveycited by 19
  6. 2024V2X-R: Cooperative LiDAR-4D Radar Fusion with Denoising Diffusion for 3D Object Detectioncited by 18
  7. 2023Human-centric Scene Understanding for 3D Large-scale Scenarioscited by 17
  8. 2024Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologiescited by 17
  9. 2024Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Imagecited by 14
  10. 2024PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Modelscited by 9
  11. 2024ContextualFusion: Context-Based Multi-Sensor Fusion for 3D Object Detection in Adverse Operating Conditionscited by 7
  12. 2024Improved Canonicalization for Model Agnostic Equivariancecited by 7
38 more
  1. 2024CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformercited by 7
  2. 2024TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weathercited by 7
  3. 2023CurveCloudNet: Processing Point Clouds with 1D Structurecited by 5
  4. 2025INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomycited by 5
  5. 2025INSTINCT: Instance-Level Interaction Architecture for Query-Based Collaborative Perceptioncited by 5
  6. 2025Towards Accurate and Efficient 3D Object Detection for Autonomous Driving: A Mixture of Experts Computing System on Edgecited by 4
  7. 2025Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Cloudscited by 3
  8. 2023LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Drivingcited by 2
  9. 2024NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloudcited by 2
  10. 2024SeePerSea: Multi-modal Perception Dataset of In-water Objects for Autonomous Surface Vehiclescited by 2
  11. 2024Semi-Supervised 3D Object Detection with Channel Augmentation using Transformation Equivariancecited by 2
  12. 2024Current Symmetry Group Equivariant Convolution Frameworks for Representation Learningcited by 2
  13. 2025RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learningcited by 2
  14. 2025A Multimodal Hybrid Late-Cascade Fusion Network for Enhanced 3D Object Detectioncited by 2
  15. 2025Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenescited by 2
  16. 2025Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completioncited by 2
  17. 2025CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Predictioncited by 2
  18. 2025Towards Open-Vocabulary Multimodal 3D Object Detection with Attributescited by 2
  19. 2025All You Need for Object Detection: From Pixels, Points, and Prompts to Next-Gen Fusion and Multimodal LLMs/VLMs in Autonomous Vehiclescited by 2
  20. 2026RADE-Net: Robust Attention Network for Radar-Only Object Detection in Adverse Weathercited by 2
  21. 2024Leveraging Anchor-based LiDAR 3D Object Detection via Point Assisted Sample Selectioncited by 1
  22. 2024EffiPerception: an Efficient Framework for Various Perception Taskscited by 1
  23. 2024Enhanced Object Detection: A Study on Vast Vocabulary Object Detection Track for V3Det Challenge 2024cited by 1
  24. 2024Boosting 3D Object Detection with Semantic-Aware Multi-Branch Frameworkcited by 1
  25. 2024RIDE: Boosting 3D Object Detection for LiDAR Point Clouds via Rotation-Invariant Analysiscited by 1
  26. 2024Enhancing 3D Robotic Vision Robustness by Minimizing Adversarial Mutual Information through a Curriculum Training Approachcited by 1
  27. 2025GeoTeacher: Geometry-Guided Semi-Supervised 3D Object Detectioncited by 1
  28. 2023Group Equivariant BEV for 3D Object Detectioncited by 0
  29. 2023VirtualPainting: Addressing Sparsity with Virtual Points and Distance-Aware Data Augmentation for 3D Object Detectioncited by 0
  30. 2024Hybrid Pooling and Convolutional Network for Improving Accuracy and Training Convergence Speed in Object Detectioncited by 0
  31. 2024Image-Guided Semantic Pseudo-LiDAR Point Generation for 3D Object Detectioncited by 0
  32. 2024VaLID: Verification as Late Integration of Detections for LiDAR-Camera Fusioncited by 0
  33. 2024Twin Trigger Generative Networks for Backdoor Attacks against Object Detectioncited by 0
  34. 2025Efficient Multimodal 3D Object Detector via Instance-Level Contrastive Distillationcited by 0
  35. 2025RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completioncited by 0
  36. 2025LDRFusion: A LiDAR-Dominant multimodal refinement framework for 3D object detectioncited by 0
  37. 2026Point Virtual Transformercited by 0
  38. 2026RadarXFormer: Robust Object Detection via Cross-Dimension Fusion of 4D Radar Spectra and Images for Autonomous Drivingcited by 0

50 most cited of 52 All 52 (JSON)