mlsanityData to 14 Oct 2026

Deep Fitting Degree Scoring Network for Monocular 3D Object Detection

arXiv 1904.12681 ↗First posted 26 Apr 2019cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose to learn a deep fitting degree scoring network for monocular 3D object detection, which aims to score fitting degree between proposals and object conclusively. Different from most existing monocular frameworks which use tight constraint to get 3D location, our approach achieves high-precision localization through measuring the visual fitting degree between the projected 3D proposals and the object. We first regress the dimension and orientation of the object using an anchor-based method so that a suitable 3D proposal can be constructed. We propose FQNet, which can infer the 3D IoU between the 3D proposals and the object solely based on 2D cues. Therefore, during the detection process, we sample a large number of candidates in the 3D space and project these 3D bounding boxes on 2D image individually. The best candidate can be picked out by simply exploring the spatial overlap between proposals and the object, in the form of the output 3D IoU score of FQNet. Experiments on the KITTI dataset demonstrate the effectiveness of our framework.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 30; 2022: 23; 2023: 10; 2024: 3; 2025: 1.

67 papers.

Sort:

By area:

  1. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  2. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  3. 2022BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Drivingcited by 191
  4. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  5. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  8. 2021Geometry-based Distance Decomposition for Monocular 3D Object Detectioncited by 84
  9. 2022Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Taskcited by 81
  10. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  11. 2021GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detectioncited by 66
  12. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
38 more
  1. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  2. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  3. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  4. 2022MonoGround: Detecting Monocular 3D Objects from the Groundcited by 37
  5. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  6. 2021The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detectioncited by 34
  7. 2022Efficient Multi-Task RGB-D Scene Analysis for Indoor Environmentscited by 33
  8. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  9. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  10. 2021FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detectioncited by 29
  11. 2022Homography Loss for Monocular 3D Object Detectioncited by 24
  12. 2022OPA-3D: Occlusion-Aware Pixel-Wise Aggregation for Monocular 3D Object Detectioncited by 24
  13. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  14. 2022Aerial Monocular 3D Object Detectioncited by 23
  15. 2023MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contextscited by 21
  16. 2021MonoGRNet: A General Framework for Monocular 3D Object Detectioncited by 20
  17. 2021Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Imagecited by 20
  18. 2022WeakM3D: Towards Weakly Supervised Monocular 3D Object Detectioncited by 18
  19. 2023Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistencycited by 18
  20. 2023MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformercited by 18
  21. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
  22. 2021MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentationcited by 16
  23. 2021IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Imagecited by 15
  24. 2023ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detectioncited by 14
  25. 2021Advancing Self-supervised Monocular Depth Learning with Sparse LiDARcited by 13
  26. 2021SGM3D: Stereo Guided Monocular 3D Object Detectioncited by 13
  27. 2021Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Datacited by 11
  28. 2021Lite-FPN for Keypoint-based Monocular 3D Object Detectioncited by 10
  29. 2022DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsetscited by 10
  30. 2023MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimationcited by 9
  31. 2021OCM3D: Object-Centric Monocular 3D Object Detectioncited by 8
  32. 20212.5D Visual Relationship Detectioncited by 7
  33. 2022Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervisioncited by 7
  34. 2023Efficient Multi-Task Scene Analysis with RGB-D Transformerscited by 7
  35. 2024General Geometry-aware Weakly Supervised 3D Object Detectioncited by 7
  36. 2022USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Drivingcited by 5
  37. 2023GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detectioncited by 5
  38. 2022"The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mappingcited by 4

50 most cited of 67 All 67 (JSON)