mlsanityData to 13 Oct 2026

FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection

arXiv 2105.07647 ↗First posted 17 May 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate the problem of weakly supervised 3D vehicle detection. Conventional methods for 3D object detection need vast amounts of manually labelled 3D data as supervision signals. However, annotating large datasets requires huge human efforts, especially for 3D area. To tackle this problem, we propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. For the first stage, a context-aware adaptive region growing algorithm is designed to segment objects based on 2D bounding boxes. Leveraging predicted segmentation masks, we develop an anti-noise approach to estimate 3D bounding boxes in the second stage. Finally 3D pseudo labels generated by our method are utilized to train a 3D detector. Independent of any 3D groundtruth, FGR reaches comparable performance with fully supervised methods on the KITTI dataset. The findings indicate that it is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.

Key facts. Cited by 29 papers in the map (data through 13 Oct 2026). Builds on 46 of its 54 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

46 of 54 references.

References · 46

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,550
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,625
  4. 2017Mask R-CNNcited by 7,266
  5. 2016Densely Connected Convolutional Networkscited by 6,707
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  8. 2015SSD: Single Shot MultiBox Detectorcited by 3,128
  9. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,096
  10. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,709
  11. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  12. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
34 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 722
  2. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  3. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  4. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  5. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  6. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 367
  7. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  8. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  9. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  10. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  11. 2019Disentangling Monocular 3D Object Detectioncited by 215
  12. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  13. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  14. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  15. 2019Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detectioncited by 124
  16. 2016Fully Convolutional Instance-aware Semantic Segmentationcited by 122
  17. 2019Fast Point R-CNNcited by 119
  18. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  19. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  20. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  21. 2019Deep Fitting Degree Scoring Network for Monocular 3D Object Detectioncited by 67
  22. 2020Weakly Supervised 3D Object Detection from Lidar Point Cloudcited by 67
  23. 2020Weakly Supervised 3D Object Detection from Point Cloudscited by 41
  24. 2019Object-Centric Stereo Matching for 3D Object Detectioncited by 29
  25. 2019Transferable Semi-supervised 3D Object Detection from RGB-D Datacited by 22
  26. 2018Quantization Mimic: Towards Very Tiny CNN for Object Detectioncited by 20
  27. 2020PointTrackNet: An End-to-End Network For 3-D Object Detection and Tracking From Point Cloudscited by 20
  28. 2019Learning 2D to 3D Lifting for Object Detection in 3D for Autonomous Vehiclescited by 18
  29. 2020SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloudcited by 16
  30. 2019LiDAR-Flow: Dense Scene Flow Estimation from Sparse LiDAR and Stereo Imagescited by 12
  31. 2019Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimationcited by 8
  32. 2019Frustum VoxNet for 3D object detection from RGB-D or Depth imagescited by 8
  33. 2020Finding Your (3D) Center: 3D Object Detection Using a Learned Losscited by 5
  34. 2019Conditional Single-view Shape Generation for Multi-view Stereo Reconstructioncited by 3

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 8; 2024: 7; 2025: 7; 2026: 1.

29 papers.

Sort:

  1. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  2. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  3. 2024Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environmentscited by 21
  4. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  5. 2023DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detectioncited by 18
  6. 2022Multimodal Transformer for Automatic 3D Annotation and Object Detectioncited by 10
  7. 2022MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generatorcited by 9
  8. 2022WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labelscited by 9
  9. 2023Weakly Supervised 3D Object Detection via Multi-Level Visual Guidancecited by 9
  10. 2024Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scenecited by 7
  11. 2024General Geometry-aware Weakly Supervised 3D Object Detectioncited by 7
  12. 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labelscited by 7
17 more
  1. 2024Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Promptscited by 6
  2. 2025OpenBox: Annotate Any Bounding Boxes in 3Dcited by 6
  3. 2023Context-Aware Transformer for 3D Point Cloud Automatic Annotationcited by 5
  4. 2023MWSIS: Multimodal Weakly Supervised Instance Segmentation with 2D Box Annotations for Autonomous Drivingcited by 5
  5. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  6. 2022Towards 3D Object Detection with 2D Supervisioncited by 3
  7. 2024Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?cited by 2
  8. 2024Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perceptioncited by 2
  9. 2025MonoSOWA: Scalable monocular 3D Object detector Without human Annotationscited by 2
  10. 2024ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Onlycited by 1
  11. 2025CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detectioncited by 1
  12. 2025Multi-Modal Assistance for Unsupervised Domain Adaptation on Point Cloud 3D Object Detectioncited by 1
  13. 2023MEDL-U: Uncertainty-aware 3D Automatic Annotation based on Evidential Deep Learningcited by 0
  14. 20232DDATA: 2D Detection Annotations Transmittable Aggregation for Semantic Segmentation on Point Cloudcited by 0
  15. 2023WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detectioncited by 0
  16. 2025MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detectioncited by 0
  17. 2026Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learningcited by 0