mlsanityData to 7 Oct 2026

Categorical Depth Distribution Network for Monocular 3D Object Detection

arXiv 2103.01100 ↗First posted 1 Mar 2021cs.CVcited by 326

Not on the map. Why?

Abstract (arXiv)

Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object depth, which must be inferred from object and scene cues due to the lack of direct range measurement. Many methods attempt to directly estimate depth to assist in 3D detection, but show limited performance as a result of depth inaccuracy. Our proposed solution, Categorical Depth Distribution Network (CaDDN), uses a predicted categorical depth distribution for each pixel to project rich contextual feature information to the appropriate depth interval in 3D space. We then use the computationally efficient bird's-eye-view projection and single-stage detector to produce the final output bounding boxes. We design CaDDN as a fully differentiable end-to-end approach for joint depth estimation and object detection. We validate our approach on the KITTI 3D object detection benchmark, where we rank 1st among published monocular methods. We also provide the first monocular 3D detection results on the newly released Waymo Open Dataset. We provide a code release for CaDDN which is made available.

Key facts. Cited by 326 papers in the map (data through 7 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 1 Mar 2021.

Builds on

53 of 66 references.

References · 53

  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. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  11. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  12. 2017Focal Loss for Dense Object Detectioncited by 749
38 more
  1. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  2. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  3. 2014Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecturecited by 483
  4. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  5. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  6. 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
  7. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  8. 2017Joint 3D Proposal Generation and Object Detection from View Aggregationcited by 325
  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. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  12. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 223
  13. 2019Disentangling Monocular 3D Object Detectioncited by 215
  14. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  15. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  16. 2020Predicting Semantic Map Representations from Images using Pyramid Occupancy Networkscited by 175
  17. 2019Cross-view Semantic Segmentation for Sensing Surroundingscited by 173
  18. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  19. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  20. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  21. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  22. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  23. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  24. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  25. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  26. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  27. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  28. 2018In Defense of Classical Image Processing: Fast Depth Completion on the CPUcited by 96
  29. 2017Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular imagecited by 95
  30. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  31. 2020MonoLayout: Amodal scene layout from a single imagecited by 49
  32. 2019Towards Generalization Across Depth for Monocular 3D Object Detectioncited by 41
  33. 2020BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloudcited by 38
  34. 2018Learning to Look around Objects for Top-View Representations of Outdoor Scenescited by 37
  35. 2019Object-Centric Stereo Matching for 3D Object Detectioncited by 29
  36. 2020Center3D: Center-based Monocular 3D Object Detection with Joint Depth Understandingcited by 25
  37. 2020Monocular Differentiable Rendering for Self-Supervised 3D Object Detectioncited by 23
  38. 2018A Parametric Top-View Representation of Complex Road Scenescited by 20

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 88; 2023: 91; 2024: 74; 2025: 39; 2026: 14.

326 papers.

Sort:

By area:

  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  4. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 550
  5. 2023Tri-Perspective View for Vision-Based 3D Semantic Occupancy Predictioncited by 404
  6. 2022BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detectioncited by 340
  7. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  8. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  9. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 287
  10. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 270
  11. 2022Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Mapscited by 255
  12. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
38 more
  1. 2024GenAD: Generative End-to-End Autonomous Drivingcited by 225
  2. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  3. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  4. 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Drivingcited by 168
  5. 2021Multimodal Virtual Point 3D Detectioncited by 166
  6. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  7. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  8. 2022Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wildcited by 159
  9. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 155
  10. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  11. 2023SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videoscited by 149
  12. 2022PolarFormer: Multi-camera 3D Object Detection with Polar Transformercited by 147
  13. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  14. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  15. 2022Vision-Centric BEV Perception: A Surveycited by 126
  16. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  17. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  18. 2023FB-BEV: BEV Representation from Forward-Backward View Transformationscited by 98
  19. 2023COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Predictioncited by 94
  20. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 90
  21. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  22. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 85
  23. 2023Collaboration Helps Camera Overtake LiDAR in 3D Detectioncited by 81
  24. 2023CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perceptioncited by 81
  25. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  26. 2023GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformerscited by 75
  27. 2023BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detectioncited by 74
  28. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  29. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  30. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  31. 2024Communication-Efficient Collaborative Perception via Information Filling with Codebookcited by 67
  32. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  33. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  34. 2022CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformercited by 66
  35. 2023LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusioncited by 57
  36. 2022Uncertainty-aware Vision-based Metric Cross-view Geolocalizationcited by 54
  37. 2022Polar Parametrization for Vision-based Surround-View 3D Detectioncited by 53
  38. 2022Voxel Field Fusion for 3D Object Detectioncited by 50

50 most cited of 326 All 326 (JSON)