mlsanityData to 7 Oct 2026

BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereo

arXiv 2304.04185 ↗First posted 9 Apr 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Bounded by the inherent ambiguity of depth perception, contemporary multi-view 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is the natural knowledge for tackling this ambiguity. However, traditional attempts of MVS has two limitations when applying to 3D object detection scenes: 1) The affinity measurement among all views suffers expensive computational cost; 2) It is difficult to deal with outdoor scenarios where objects are often mobile. To this end, we propose BEVStereo++: by introducing a dynamic temporal stereo strategy, BEVStereo++ is able to cut down the harm that is brought by introducing temporal stereo when dealing with those two scenarios. Going one step further, we apply Motion Compensation Module and long sequence Frame Fusion to BEVStereo++, which shows further performance boosting and error reduction. Without bells and whistles, BEVStereo++ achieves state-of-the-art(SOTA) on both Waymo and nuScenes dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 41 of its 44 references that are in the map. First posted on arXiv 9 Apr 2023.

Builds on

41 of 44 references.

References · 41

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  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. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
  7. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  8. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  9. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  11. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  12. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
29 more
  1. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  2. 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  4. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  5. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  6. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  7. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  8. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 351
  9. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  10. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  11. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  12. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
  13. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  14. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  15. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  16. 2022M2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representationcited by 155
  17. 2019Point-Based Multi-View Stereo Networkcited by 147
  18. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  19. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  20. 2022BEVPoolv2: A Cutting-edge Implementation of BEVDet Toward Deploymentcited by 79
  21. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  22. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  23. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46
  24. 2020Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimationcited by 43
  25. 2022Monocular 3D Object Detection with Depth from Motioncited by 38
  26. 2021YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detectioncited by 34
  27. 2022MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbonescited by 29
  28. 2022DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detectioncited by 25
  29. 2021Deep Learning for Multi-View Stereo via Plane Sweep: A Surveycited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2023PointBeV: A Sparse Approach to BeV Predictionscited by 23
  2. 2024CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Predictioncited by 23
  3. 2024OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networkscited by 17
  4. 2026Towards Efficient 3D Object Detection for Vehicle-Infrastructure Collaboration via Risk-Intent Selectioncited by 0