mlsanityData to 7 Oct 2026

YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

arXiv 2103.09422 ↗First posted 17 Mar 2021cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://github.com/Owen-Liuyuxuan/visualDet3D.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 17 Mar 2021.

Builds on

28 of 35 references.

References · 28

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Fast R-CNNcited by 2,930
  3. 2018Pyramid Stereo Matching Networkcited by 486
  4. 2018Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivingcited by 455
  5. 2019GhostNet: More Features from Cheap Operationscited by 410
  6. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  7. 2019M3D-RPN: Monocular 3D Region Proposal Network for Object Detectioncited by 251
  8. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  9. 2019End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Cloudscited by 171
  10. 2019Learning Depth-Guided Convolutions for Monocular 3D Object Detectioncited by 169
  11. 2019Stereo R-CNN based 3D Object Detection for Autonomous Drivingcited by 163
  12. 2020MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationshipscited by 153
16 more
  1. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  2. 2020RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Drivingcited by 150
  3. 2019Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Drivingcited by 137
  4. 2019Monocular 3D Object Detection with Pseudo-LiDAR Point Cloudcited by 113
  5. 2020DSGN: Deep Stereo Geometry Network for 3D Object Detectioncited by 100
  6. 2019How do neural networks see depth in single images?cited by 82
  7. 2020End-to-End Pseudo-LiDAR for Image-Based 3D Object Detectioncited by 80
  8. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  9. 2021Ground-aware Monocular 3D Object Detection for Autonomous Drivingcited by 65
  10. 2019Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matchingcited by 55
  11. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  12. 2020FADNet: A Fast and Accurate Network for Disparity Estimationcited by 31
  13. 2019Object-Centric Stereo Matching for 3D Object Detectioncited by 29
  14. 2020ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detectioncited by 25
  15. 2019RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Drivingcited by 23
  16. 2018Focal Loss in 3D Object Detectioncited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 7; 2023: 13; 2024: 2; 2025: 5; 2026: 1.

34 papers.

Sort:

  1. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  2. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  3. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  4. 2021AutoShape: Real-Time Shape-Aware Monocular 3D Object Detectioncited by 87
  5. 2022Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Drivingcited by 30
  6. 2023Object Detection with Transformers: A Reviewcited by 22
  7. 2023MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddingscited by 20
  8. 2021SGM3D: Stereo Guided Monocular 3D Object Detectioncited by 13
  9. 2022DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectorscited by 10
  10. 2023SSD-MonoDETR: Supervised Scale-aware Deformable Transformer for Monocular 3D Object Detectioncited by 9
  11. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  12. 2023Vision-based Learning for Drones: A Surveycited by 9
22 more
  1. 2022ORA3D: Overlap Region Aware Multi-view 3D Object Detectioncited by 8
  2. 2021ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detectioncited by 7
  3. 2023StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detectioncited by 7
  4. 2023Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Trainingcited by 5
  5. 2023BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereocited by 4
  6. 2022FFPA-Net: Efficient Feature Fusion with Projection Awareness for 3D Object Detectioncited by 3
  7. 2024You Only Look Bottom-Up for Monocular 3D Object Detectioncited by 3
  8. 2025Unleashing the Temporal Potential of Stereo Event Cameras for Continuous-Time 3D Object Detectioncited by 3
  9. 2023Transformer-based stereo-aware 3D object detection from binocular imagescited by 2
  10. 2025Stereo-based 3D Anomaly Object Detection for Autonomous Driving: A New Dataset and Baselinecited by 2
  11. 2025CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Predictioncited by 2
  12. 2025StereoDETR: Stereo-based Transformer for 3D Object Detectioncited by 2
  13. 2021Joint stereo 3D object detection and implicit surface reconstructioncited by 1
  14. 2023MonoNext: A 3D Monocular Object Detection with ConvNextcited by 1
  15. 2024Real-time Stereo-based 3D Object Detection for Streaming Perceptioncited by 1
  16. 2026DDStereo: Efficient Dual Decoder Transformers for Stereo 3D Road Anomaly Detectioncited by 1
  17. 2021Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detectioncited by 0
  18. 2022MDS-Net: A Multi-scale Depth Stratification Based Monocular 3D Object Detection Algorithmcited by 0
  19. 2023VCVW-3D: A Virtual Construction Vehicles and Workers Dataset with 3D Annotationscited by 0
  20. 2023Monocular 2D Camera-based Proximity Monitoring for Human-Machine Collision Warning on Construction Sitescited by 0
  21. 2023S3-MonoDETR: Supervised Shape&Scale-perceptive Deformable Transformer for Monocular 3D Object Detectioncited by 0
  22. 2025How good are deep learning methods for automated road safety analysis using video data? An experimental studycited by 0