mlsanityData to 7 Oct 2026

PersDet: Monocular 3D Detection in Perspective Bird's-Eye-View

arXiv 2208.09394 ↗First posted 19 Aug 2022cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These operators are not supported on many edge devices, bringing extra obstacles when deploying detectors. To address this problem, we revisit the generation of BEV representation and propose detecting objects in perspective BEV -- a new BEV representation that does not require feature sampling. We demonstrate that perspective BEV features can likewise enjoy the benefits of the BEV paradigm. Moreover, the perspective BEV improves detection performance by addressing issues caused by feature sampling. We propose PersDet for high-performance object detection in perspective BEV space based on this discovery. While implementing a simple and memory-efficient structure, PersDet outperforms existing state-of-the-art monocular methods on the nuScenes benchmark, reaching 34.6% mAP and 40.8% NDS when using ResNet-50 as the backbone.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 23 of its 29 references that are in the map. First posted on arXiv 19 Aug 2022.

Builds on

23 of 29 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  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. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  8. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  9. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  12. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 444
11 more
  1. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  2. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  3. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  4. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  5. 2019Disentangling Monocular 3D Object Detectioncited by 215
  6. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  7. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  8. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  9. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 173
  10. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  11. 2019Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Losscited by 30

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2.

3 papers.

  1. 2022BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detectioncited by 4
  2. 2023One Training for Multiple Deployments: Polar-based Adaptive BEV Perception for Autonomous Drivingcited by 3
  3. 2023A Dynamic Feature Interaction Framework for Multi-task Visual Perceptioncited by 2