mlsanityData to 7 Oct 2026

M3DSSD: Monocular 3D Single Stage Object Detector

arXiv 2103.13164 ↗First posted 24 Mar 2021cs.CVcited by 39

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a Monocular 3D Single Stage object Detector (M3DSSD) with feature alignment and asymmetric non-local attention. Current anchor-based monocular 3D object detection methods suffer from feature mismatching. To overcome this, we propose a two-step feature alignment approach. In the first step, the shape alignment is performed to enable the receptive field of the feature map to focus on the pre-defined anchors with high confidence scores. In the second step, the center alignment is used to align the features at 2D/3D centers. Further, it is often difficult to learn global information and capture long-range relationships, which are important for the depth prediction of objects. Therefore, we propose a novel asymmetric non-local attention block with multi-scale sampling to extract depth-wise features. The proposed M3DSSD achieves significantly better performance than the monocular 3D object detection methods on the KITTI dataset, in both 3D object detection and bird's eye view tasks.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Builds on 39 of its 47 references that are in the map. First posted on arXiv 24 Mar 2021.

Builds on

39 of 47 references.

References · 39

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2017Non-local Neural Networkscited by 2,290
  3. 2019Objects as Pointscited by 1,172
  4. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  5. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  6. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  7. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  8. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  9. 2017Deep Layer Aggregationcited by 436
  10. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  11. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  12. 20163D Bounding Box Estimation Using Deep Learning and Geometrycited by 277
27 more
  1. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  2. 2019Disentangling Monocular 3D Object Detectioncited by 215
  3. 2020Multi-Task Multi-Sensor Fusion for 3D Object Detectioncited by 203
  4. 2020SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimationcited by 202
  5. 2018Orthographic Feature Transform for Monocular 3D Object Detectioncited by 201
  6. 2019Asymmetric Non-local Neural Networks for Semantic Segmentationcited by 196
  7. 2017PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimationcited by 170
  8. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  9. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  10. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
  11. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  12. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  13. 2018A2-Nets: Double Attention Networkscited by 136
  14. 2019GS3D: An Efficient 3D Object Detection Framework for Autonomous Drivingcited by 106
  15. 2019Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstructioncited by 106
  16. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  17. 2017Deep MANTA: A Coarse-to-fine Many-Task Network for joint 2D and 3D vehicle analysis from monocular imagecited by 95
  18. 2019Region Proposal by Guided Anchoringcited by 87
  19. 2018MonoGRNet: A Geometric Reasoning Network for Monocular 3D Object Localizationcited by 84
  20. 20163D Object Proposals using Stereo Imagery for Accurate Object Class Detectioncited by 58
  21. 2020Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimationcited by 43
  22. 2019Triangulation Learning Network: from Monocular to Stereo 3D Object Detectioncited by 40
  23. 2019Monocular 3D Object Detection via Geometric Reasoning on Keypointscited by 31
  24. 2019Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Losscited by 30
  25. 2019Shift R-CNN: Deep Monocular 3D Object Detection with Closed-Form Geometric Constraintscited by 25
  26. 2019RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Drivingcited by 23
  27. 2019Revisiting Feature Alignment for One-stage Object Detectioncited by 14

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 17; 2023: 7; 2024: 3; 2025: 2.

39 papers.

Sort:

By area:

  1. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  2. 2022MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformercited by 108
  3. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  4. 2021GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detectioncited by 66
  5. 2021Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detectioncited by 66
  6. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  7. 2022Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detectioncited by 48
  8. 2023UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye Viewcited by 43
  9. 2023GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detectioncited by 34
  10. 2021Autonomy 2.0: Why is self-driving always 5 years away?cited by 30
  11. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  12. 2022MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detectioncited by 30
27 more
  1. 2022EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queriescited by 25
  2. 2022Homography Loss for Monocular 3D Object Detectioncited by 24
  3. 2021From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decodercited by 23
  4. 2022Boosting 3D Object Detection by Simulating Multimodality on Point Cloudscited by 22
  5. 2021Exploring Geometric Consistency for Monocular 3D Object Detectioncited by 17
  6. 2024MultiCorrupt: A Multi-Modal Robustness Dataset and Benchmark of LiDAR-Camera Fusion for 3D Object Detectioncited by 17
  7. 2021MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentationcited by 15
  8. 2023ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detectioncited by 14
  9. 2021Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloudcited by 13
  10. 2021Lite-FPN for Keypoint-based Monocular 3D Object Detectioncited by 10
  11. 2024MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detectioncited by 10
  12. 2023Weakly Supervised 3D Object Detection via Multi-Level Visual Guidancecited by 9
  13. 2023PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detectioncited by 8
  14. 2025VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regionscited by 7
  15. 2022Shape-Aware Monocular 3D Object Detectioncited by 6
  16. 2022Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Cloudscited by 6
  17. 2022Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detectioncited by 5
  18. 2022From a Bird's Eye View to See: Joint Camera and Subject Registration without the Camera Calibrationcited by 5
  19. 2022An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detectioncited by 2
  20. 2025CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Predictioncited by 2
  21. 2021SoK: Vehicle Orientation Representations for Deep Rotation Estimationcited by 1
  22. 2022EAA-Net: Rethinking the Autoencoder Architecture with Intra-class Features for Medical Image Segmentationcited by 1
  23. 2021Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detectioncited by 0
  24. 2022MonoSIM: Simulating Learning Behaviors of Heterogeneous Point Cloud Object Detectors for Monocular 3D Object Detectioncited by 0
  25. 2023Understanding Depth Map Progressively: Adaptive Distance Interval Separation for Monocular 3d Object Detectioncited by 0
  26. 2023S3-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detectioncited by 0
  27. 2024Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detectioncited by 0