mlsanityData to 14 Oct 2026

OCM3D: Object-Centric Monocular 3D Object Detection

arXiv 2104.06041 ↗First posted 13 Apr 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Image-only and pseudo-LiDAR representations are commonly used for monocular 3D object detection. However, methods based on them have shortcomings of either not well capturing the spatial relationships in neighbored image pixels or being hard to handle the noisy nature of the monocular pseudo-LiDAR point cloud. To overcome these issues, in this paper we propose a novel object-centric voxel representation tailored for monocular 3D object detection. Specifically, voxels are built on each object proposal, and their sizes are adaptively determined by the 3D spatial distribution of the points, allowing the noisy point cloud to be organized effectively within a voxel grid. This representation is proved to be able to locate the object in 3D space accurately. Furthermore, prior works would like to estimate the orientation via deep features extracted from an entire image or a noisy point cloud. By contrast, we argue that the local RoI information from the object image patch alone with a proper resizing scheme is a better input as it provides complete semantic clues meanwhile excludes irrelevant interferences. Besides, we decompose the confidence mechanism in monocular 3D object detection by considering the relationship between 3D objects and the associated 2D boxes. Evaluated on KITTI, our method outperforms state-of-the-art methods by a large margin. The code will be made publicly available soon.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 39 of its 42 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

39 of 42 references.

References · 39

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,715
  6. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  9. 2019Objects as Pointscited by 1,175
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  11. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  12. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 457
27 more
  1. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  2. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 382
  3. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 368
  4. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  5. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  6. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 278
  7. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 252
  8. 2019Disentangling Monocular 3D Object Detectioncited by 217
  9. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 202
  10. 20203D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detectioncited by 176
  11. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  12. 2020EPNet: Enhancing Point Features with Image Semantics for 3D Object Detectioncited by 164
  13. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  14. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  15. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  16. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  17. 2018ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shapecited by 123
  18. 2020Kinematic 3D Object Detection in Monocular Videocited by 116
  19. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  20. 2020Rethinking Pseudo-LiDAR Representationcited by 109
  21. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  22. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 101
  23. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  24. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  25. 2019Deep Fitting Degree Scoring Network for Monocular 3D Object Detectioncited by 67
  26. 20163D Object Proposals using Stereo Imagery for Accurate Object Class Detectioncited by 58
  27. 2019Voxel-FPN: multi-scale voxel feature aggregation in 3D object detection from point cloudscited by 9

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 4.

8 papers.

  1. 2022DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detectioncited by 39
  2. 2021Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overviewcited by 31
  3. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  4. 2021Lidar Point Cloud Guided Monocular 3D Object Detectioncited by 29
  5. 2022WeakM3D: Towards Weakly Supervised Monocular 3D Object Detectioncited by 18
  6. 2022OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detectioncited by 5
  7. 2021Joint stereo 3D object detection and implicit surface reconstructioncited by 1
  8. 2021SoK: Vehicle Orientation Representations for Deep Rotation Estimationcited by 1