mlsanityData to 7 Oct 2026

WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection

arXiv 2203.08332 ↗First posted 16 Mar 2022cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D box labels on the LiDAR point clouds. This annotation process is very laborious and expensive. To dispense with the reliance on 3D box labels, in this paper we explore the weakly supervised monocular 3D detection. Specifically, we first detect 2D boxes on the image. Then, we adopt the generated 2D boxes to select corresponding RoI LiDAR points as the weak supervision. Eventually, we adopt a network to predict 3D boxes which can tightly align with associated RoI LiDAR points. This network is learned by minimizing our newly-proposed 3D alignment loss between the 3D box estimates and the corresponding RoI LiDAR points. We will illustrate the potential challenges of the above learning problem and resolve these challenges by introducing several effective designs into our method. Codes will be available at https://github.com/SPengLiang/WeakM3D.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 40 of its 48 references that are in the map. First posted on arXiv 16 Mar 2022.

Builds on

40 of 48 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Mask R-CNNcited by 7,259
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019Objects as Pointscited by 1,172
  12. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
28 more
  1. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  2. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  3. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  4. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  6. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  7. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  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. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  13. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  14. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  15. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  16. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  17. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  18. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  19. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  20. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  21. 2016Vehicle Detection from 3D Lidar Using Fully Convolutional Networkcited by 105
  22. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  23. 2019Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priorscited by 74
  24. 2019Deep Fitting Degree Scoring Network for Monocular 3D Object Detectioncited by 67
  25. 2020Weakly Supervised 3D Object Detection from Lidar Point Cloudcited by 67
  26. 20163D Object Proposals using Stereo Imagery for Accurate Object Class Detectioncited by 58
  27. 2020Weakly Supervised 3D Object Detection from Point Cloudscited by 41
  28. 2021OCM3D: Object-Centric Monocular 3D Object Detectioncited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 6; 2025: 5; 2026: 1.

18 papers.

Sort:

  1. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  2. 2023Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistencycited by 18
  3. 2024Weakly Supervised Monocular 3D Detection with a Single-View Imagecited by 10
  4. 2024General Geometry-aware Weakly Supervised 3D Object Detectioncited by 7
  5. 2024VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detectioncited by 6
  6. 2026LabelAny3D: Label Any Object 3D in the Wildcited by 6
  7. 2023Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Trainingcited by 5
  8. 2022Towards 3D Object Detection with 2D Supervisioncited by 3
  9. 2023Weakly Supervised 3D Object Detection with Multi-Stage Generalizationcited by 2
  10. 2024Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perceptioncited by 2
  11. 2024Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Datacited by 2
  12. 2025MonoSOWA: Scalable monocular 3D Object detector Without human Annotationscited by 2
6 more
  1. 2025CA-W3D: Leveraging Context-Aware Knowledge for Weakly Supervised Monocular 3D Detectioncited by 1
  2. 2025Weak Cube R-CNN: Weakly Supervised 3D Detection using only 2D Bounding Boxescited by 1
  3. 2025PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detectioncited by 1
  4. 2022Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotationscited by 0
  5. 2024Smart Feature is What You Needcited by 0
  6. 2025VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Renderingcited by 0