mlsanityData to 7 Oct 2026

Towards Stable 3D Object Detection

arXiv 2407.04305 ↗First posted 5 Jul 2024cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

In autonomous driving, the temporal stability of 3D object detection greatly impacts the driving safety. However, the detection stability cannot be accessed by existing metrics such as mAP and MOTA, and consequently is less explored by the community. To bridge this gap, this work proposes Stability Index (SI), a new metric that can comprehensively evaluate the stability of 3D detectors in terms of confidence, box localization, extent, and heading. By benchmarking state-of-the-art object detectors on the Waymo Open Dataset, SI reveals interesting properties of object stability that have not been previously discovered by other metrics. To help models improve their stability, we further introduce a general and effective training strategy, called Prediction Consistency Learning (PCL). PCL essentially encourages the prediction consistency of the same objects under different timestamps and augmentations, leading to enhanced detection stability. Furthermore, we examine the effectiveness of PCL with the widely-used CenterPoint, and achieve a remarkable SI of 86.00 for vehicle class, surpassing the baseline by 5.48. We hope our work could serve as a reliable baseline and draw the community's attention to this crucial issue in 3D object detection. Codes will be made publicly available.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 5 Jul 2024.

Builds on

44 of 53 references.

References · 44

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  4. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  5. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  6. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  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. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  11. 2016Simple Online and Realtime Trackingcited by 862
  12. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
32 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  3. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  6. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  7. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  8. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 372
  9. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  10. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  11. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  12. 2020VarifocalNet: An IoU-aware Dense Object Detectorcited by 230
  13. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  14. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  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. 2019LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Drivingcited by 133
  18. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  19. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  20. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  21. 2019Fast Point R-CNNcited by 119
  22. 2021RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detectioncited by 115
  23. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  24. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  25. 2020Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detectioncited by 78
  26. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  27. 2023PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Cloudscited by 54
  28. 2018IPOD: Intensive Point-based Object Detector for Point Cloudcited by 46
  29. 2021To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernelscited by 39
  30. 2023DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Cloudscited by 31
  31. 2023Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detectioncited by 28
  32. 2016On The Stability of Video Detection and Trackingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

7 papers.

  1. 2024OPUS: Occupancy Prediction Using a Sparse Setcited by 56
  2. 2024Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunablecited by 4
  3. 2026DSERT-RoLL: Robust Multi-Modal Perception for Diverse Driving Conditions with Stereo Event-RGB-Thermal Cameras, 4D Radar, and Dual-LiDARcited by 2
  4. 2025Rethink 3D Object Detection from Physical Worldcited by 0
  5. 2026SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Predictioncited by 0
  6. 2026Taming Perception Jitter: Uncertainty-Aware LiDAR Object Detection for Reliable Motion Classificationcited by 0
  7. 2026Comprehensive Robustness Analysis of LiDAR-based 3D Object Detection in Autonomous Drivingcited by 0