mlsanityData to 14 Oct 2026

Shape-Aware Monocular 3D Object Detection

arXiv 2204.08717 ↗First posted 19 Apr 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

The detection of 3D objects through a single perspective camera is a challenging issue. The anchor-free and keypoint-based models receive increasing attention recently due to their effectiveness and simplicity. However, most of these methods are vulnerable to occluded and truncated objects. In this paper, a single-stage monocular 3D object detection model is proposed. An instance-segmentation head is integrated into the model training, which allows the model to be aware of the visible shape of a target object. The detection largely avoids interference from irrelevant regions surrounding the target objects. In addition, we also reveal that the popular IoU-based evaluation metrics, which were originally designed for evaluating stereo or LiDAR-based detection methods, are insensitive to the improvement of monocular 3D object detection algorithms. A novel evaluation metric, namely average depth similarity (ADS) is proposed for the monocular 3D object detection models. Our method outperforms the baseline on both the popular and the proposed evaluation metrics while maintaining real-time efficiency.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 41 of its 48 references that are in the map. First posted on arXiv 19 Apr 2022.

Builds on

41 of 48 references.

References · 41

  1. 2017Mask R-CNNcited by 7,277
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
  6. 2018Group Normalizationcited by 1,524
  7. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,368
  8. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  9. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  10. 2019Objects as Pointscited by 1,175
  11. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  12. 2018Albumentations: fast and flexible image augmentationscited by 560
29 more
  1. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
  2. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  3. 2017Deep Layer Aggregationcited by 436
  4. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  5. 2019Class-balanced Grouping and Sampling for Point Cloud 3D Object Detectioncited by 350
  6. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 327
  7. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  8. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 249
  9. 2019Disentangling Monocular 3D Object Detectioncited by 217
  10. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 204
  11. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  12. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  13. 2021Objects are Different: Flexible Monocular 3D Object Detectioncited by 185
  14. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  15. 2021Geometry Uncertainty Projection Network for Monocular 3D Object Detectioncited by 156
  16. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  17. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  18. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 140
  19. 2021Probabilistic two-stage detectioncited by 130
  20. 2017Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular imagecited by 95
  21. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  22. 2021MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagationcited by 82
  23. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 67
  24. 2021Ground-aware Monocular 3D Object Detection for Autonomous Drivingcited by 65
  25. 2020Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimationcited by 43
  26. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  27. 2021M3DSSD: Monocular 3D Single Stage Object Detectorcited by 39
  28. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  29. 2020Are we Missing Confidence in Pseudo-LiDAR Methods for Monocular 3D Object Detection?cited by 27

Built on by

Cited by year (2026 to 14 Oct)

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

6 papers.

  1. 2023MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddingscited by 22
  2. 2023V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Networkcited by 2
  3. 2023S3-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detectioncited by 0
  4. 2024Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detectioncited by 0
  5. 2025OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perceptioncited by 0
  6. 2026Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detectioncited by 0