mlsanityData to 7 Oct 2026

ORA3D: Overlap Region Aware Multi-view 3D Object Detection

arXiv 2207.00865 ↗First posted 2 Jul 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Current multi-view 3D object detection methods often fail to detect objects in the overlap region properly, and the networks' understanding of the scene is often limited to that of a monocular detection network. Moreover, objects in the overlap region are often largely occluded or suffer from deformation due to camera distortion, causing a domain shift. To mitigate this issue, we propose using the following two main modules: (1) Stereo Disparity Estimation for Weak Depth Supervision and (2) Adversarial Overlap Region Discriminator. The former utilizes the traditional stereo disparity estimation method to obtain reliable disparity information from the overlap region. Given the disparity estimates as supervision, we propose regularizing the network to fully utilize the geometric potential of binocular images and improve the overall detection accuracy accordingly. Further, the latter module minimizes the representational gap between non-overlap and overlapping regions. We demonstrate the effectiveness of the proposed method with the nuScenes large-scale multi-view 3D object detection data. Our experiments show that our proposed method outperforms current state-of-the-art models, i.e., DETR3D and BEVDet.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 53 of its 60 references that are in the map. First posted on arXiv 2 Jul 2022.

Builds on

53 of 60 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2020End-to-End Object Detection with Transformerscited by 7,384
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  9. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  10. 2015Fast R-CNNcited by 2,930
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
38 more
  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2019Objects as Pointscited by 1,172
  3. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  4. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  5. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  6. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  7. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  8. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  9. 2018Pyramid Stereo Matching Networkcited by 486
  10. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  11. 2019PointPainting: Sequential Fusion for 3D Object Detectioncited by 449
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
  13. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  14. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  15. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  16. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  17. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  18. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  19. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  20. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  21. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  22. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  23. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  24. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  25. 2021ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detectioncited by 157
  26. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  27. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  28. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  29. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  30. 2021FusionPainting: Multimodal Fusion with Adaptive Attention for 3D Object Detectioncited by 92
  31. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  32. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  33. 2021Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detectioncited by 79
  34. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  35. 2019Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matchingcited by 55
  36. 2021YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detectioncited by 34
  37. 2020SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Cloudscited by 27
  38. 2021PLUMENet: Efficient 3D Object Detection from Stereo Imagescited by 19

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 3; 2025: 1.

8 papers.

  1. 2022Vision-Centric BEV Perception: A Surveycited by 126
  2. 2023RoboBEV: Towards Robust Bird's Eye View Perception under Corruptionscited by 42
  3. 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
  4. 2023CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perceptioncited by 14
  5. 2024Unified Domain Generalization and Adaptation for Multi-View 3D Object Detectioncited by 13
  6. 20253D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformationcited by 9
  7. 2024DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perceptioncited by 5
  8. 2023One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Drivingcited by 3