mlsanityData to 7 Oct 2026

Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection

arXiv 2103.16470 ↗First posted 30 Mar 2021cs.CVcited by 84

Not on the map. Why?

Abstract (arXiv)

The objective of this paper is to learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection. We make following contributions: (i) rather than appealing to the complicated pseudo-LiDAR based approach, we propose a depth-conditioned dynamic message propagation (DDMP) network to effectively integrate the multi-scale depth information with the image context;(ii) this is achieved by first adaptively sampling context-aware nodes in the image context and then dynamically predicting hybrid depth-dependent filter weights and affinity matrices for propagating information; (iii) by augmenting a center-aware depth encoding (CDE) task, our method successfully alleviates the inaccurate depth prior; (iv) we thoroughly demonstrate the effectiveness of our proposed approach and show state-of-the-art results among the monocular-based approaches on the KITTI benchmark dataset. Particularly, we rank 1st in the highly competitive KITTI monocular 3D object detection track on the submission day (November 16th, 2020). Code and models are released at urlhttps://github.com/fudan-zvg/DDMP

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). Builds on 43 of its 51 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

43 of 51 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Graph Attention Networkscited by 8,854
  5. 2017Mask R-CNNcited by 7,259
  6. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  9. 2017Deformable Convolutional Networkscited by 1,481
  10. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  11. 2019Objects as Pointscited by 1,172
  12. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
31 more
  1. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  2. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  3. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  4. 2018Pyramid Stereo Matching Networkcited by 486
  5. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  6. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  7. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
  8. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  9. 2019Disentangling Monocular 3D Object Detectioncited by 215
  10. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  11. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  12. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  13. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  14. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  15. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  16. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  17. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  18. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  19. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  20. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  21. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  22. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  23. 2019Deep Fitting Degree Scoring Network for Monocular 3D Object Detectioncited by 67
  24. 2019Dynamic Graph Message Passing Networkscited by 62
  25. 2020Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimationcited by 43
  26. 2020Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detectioncited by 31
  27. 2019Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Losscited by 30
  28. 2019Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraintscited by 25
  29. 2020Crossing The Gap: A Deep Dive into Zero-Shot Sim-to-Real Transfer for Dynamicscited by 20
  30. 2017Evolving Boxes for Fast Vehicle Detectioncited by 6
  31. 20203DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selectioncited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 29; 2023: 21; 2024: 14; 2025: 7; 2026: 2.

84 papers.

Sort:

By area:

  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  3. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  4. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 159
  5. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  6. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  7. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  8. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  9. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 85
  10. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  11. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  12. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
38 more
  1. 2024IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detectioncited by 57
  2. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  3. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  4. 2022Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detectioncited by 49
  5. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  6. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
  7. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 39
  8. 2024MonoCD: Monocular 3D Object Detection with Complementary Depthscited by 38
  9. 2022MonoGround: Detecting Monocular 3D Objects from the Groundcited by 37
  10. 2025Multimodal Fusion and Vision-Language Models: A Survey for Robot Visioncited by 37
  11. 2022Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detectioncited by 35
  12. 2023Learning Occupancy for Monocular 3D Object Detectioncited by 35
  13. 2023MonoNeRD: NeRF-like Representations for Monocular 3D Object Detectioncited by 33
  14. 2022MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detectioncited by 30
  15. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  16. 2022Densely Constrained Depth Estimator for Monocular 3D Object Detectioncited by 27
  17. 2022Homography Loss for Monocular 3D Object Detectioncited by 24
  18. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  19. 2024MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priorscited by 21
  20. 2021Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detectioncited by 20
  21. 2023Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistencycited by 18
  22. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
  23. 2021MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentationcited by 15
  24. 2024MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoderscited by 15
  25. 2023ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detectioncited by 14
  26. 2023SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detectioncited by 14
  27. 2021SGM3D: Stereo Guided Monocular 3D Object Detectioncited by 13
  28. 2023NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localizationcited by 13
  29. 2024Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detectioncited by 11
  30. 2025Depth Anything at Any Conditioncited by 11
  31. 2021Lite-FPN for Keypoint-based Monocular 3D Object Detectioncited by 10
  32. 2022DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectorscited by 10
  33. 2023Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learningcited by 10
  34. 2024MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detectioncited by 10
  35. 2024MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detectioncited by 10
  36. 2023SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detectioncited by 9
  37. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  38. 2022Boosting Monocular 3D Object Detection with Object-Centric Auxiliary Depth Supervisioncited by 7

50 most cited of 84 All 84 (JSON)