mlsanityData to 7 Oct 2026

3D Object Detection from Images for Autonomous Driving: A Survey

arXiv 2202.02980 ↗First posted 7 Feb 2022cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

3D object detection from images, one of the fundamental and challenging problems in autonomous driving, has received increasing attention from both industry and academia in recent years. Benefiting from the rapid development of deep learning technologies, image-based 3D detection has achieved remarkable progress. Particularly, more than 200 works have studied this problem from 2015 to 2021, encompassing a broad spectrum of theories, algorithms, and applications. However, to date no recent survey exists to collect and organize this knowledge. In this paper, we fill this gap in the literature and provide the first comprehensive survey of this novel and continuously growing research field, summarizing the most commonly used pipelines for image-based 3D detection and deeply analyzing each of their components. Additionally, we also propose two new taxonomies to organize the state-of-the-art methods into different categories, with the intent of providing a more systematic review of existing methods and facilitating fair comparisons with future works. In retrospect of what has been achieved so far, we also analyze the current challenges in the field and discuss future directions for image-based 3D detection research.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). Builds on 172 of its 229 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

172 of 229 references.

References · 172

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  7. 2017Mask R-CNNcited by 7,259
  8. 2016Densely Connected Convolutional Networkscited by 6,691
  9. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  10. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  11. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  12. 2017Squeeze-and-Excitation Networkscited by 4,763
38 more
  1. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  6. 2015Fast R-CNNcited by 2,930
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  9. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  10. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  11. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  12. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  13. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  14. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  15. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  16. 2017Deformable Convolutional Networkscited by 1,481
  17. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  18. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,345
  19. 2019Objects as Pointscited by 1,172
  20. 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
  21. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  22. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  23. 2017A Survey on Multi-Task Learningcited by 838
  24. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  25. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 816
  26. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  27. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  28. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  29. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  30. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  31. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 721
  32. 2018Deep Ordinal Regression Network for Monocular Depth Estimationcited by 721
  33. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  34. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  35. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  36. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  37. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  38. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595

50 most cited of 172 All 172 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 11; 2024: 31; 2025: 13; 2026: 4.

66 papers.

Sort:

By area:

  1. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,213
  2. 2024A Survey on 3D Gaussian Splattingcited by 221
  3. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  4. 2024OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Drivingcited by 76
  5. 2023Bird's-Eye-View Scene Graph for Vision-Language Navigationcited by 71
  6. 2022DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detectioncited by 48
  7. 2025ReSim: Reliable World Simulation for Autonomous Drivingcited by 42
  8. 2024A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspectivecited by 37
  9. 2025Detect Anything 3D in the Wildcited by 32
  10. 2024Vision-based 3D occupancy prediction in autonomous driving: a review and outlookcited by 29
  11. 2024OccFlowNet: Towards Self-supervised Occupancy Estimation via Differentiable Rendering and Occupancy Flowcited by 22
  12. 2025Doracamom: Joint 3D Detection and Occupancy Prediction with Multi-view 4D Radars and Cameras for Omnidirectional Perceptioncited by 21
38 more
  1. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
  2. 2024DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detectioncited by 19
  3. 2024RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusioncited by 19
  4. 2024Data-Centric Evolution in Autonomous Driving: A Comprehensive Survey of Big Data System, Data Mining, and Closed-Loop Technologiescited by 17
  5. 2023Calibration-free BEV Representation for Infrastructure Perceptioncited by 15
  6. 2024HGSFusion: Radar-Camera Fusion with Hybrid Generation and Synchronization for 3D Object Detectioncited by 14
  7. 2024SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objectscited by 12
  8. 2024RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Networkcited by 11
  9. 2024Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlookscited by 9
  10. 2024RayFormer: Improving Query-Based Multi-Camera 3D Object Detection via Ray-Centric Strategiescited by 9
  11. 2024Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detectioncited by 9
  12. 2024Make Your ViT-based Multi-view 3D Detectors Faster via Token Compressioncited by 9
  13. 2025Unleashing the Power of Chain-of-Prediction for Monocular 3D Object Detectioncited by 8
  14. 2023OA-DET3D: Embedding Object Awareness as a General Plug-in for Multi-Camera 3D Object Detectioncited by 7
  15. 2023Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceivercited by 7
  16. 2024TripleMixer: A 3D Point Cloud Denoising Model for Adverse Weathercited by 7
  17. 2024Joint Perception and Prediction for Autonomous Driving: A Surveycited by 7
  18. 2023Every Dataset Counts: Scaling up Monocular 3D Object Detection with Joint Datasets Trainingcited by 5
  19. 2022T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Predictioncited by 4
  20. 20233D Multiple Object Tracking on Autonomous Driving: A Literature Reviewcited by 4
  21. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  22. 2024Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunablecited by 4
  23. 2025CHARM3R: Towards Unseen Camera Height Robust Monocular 3D Detectorcited by 4
  24. 2022Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detectioncited by 3
  25. 2025Enhancing 3D Semantic Scene Completion with a Refinement Modulecited by 3
  26. 2022An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detectioncited by 2
  27. 2024Debiasing surgeon: fantastic weights and how to find themcited by 2
  28. 2024EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Unioncited by 2
  29. 2024InScope: A New Real-world 3D Infrastructure-side Collaborative Perception Dataset for Open Traffic Scenarioscited by 2
  30. 2024Retina-Inspired Object Motion Segmentation for Event-Camerascited by 2
  31. 2024Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detectioncited by 2
  32. 2026The Semantic Lifecycle in Embodied AI: Acquisition, Representation and Storage via Foundation Modelscited by 2
  33. 2026Towards Intrinsic-Aware Monocular 3D Object Detectioncited by 2
  34. 2023Object Motion Sensitivity: A Bio-inspired Solution to the Ego-motion Problem for Event-based Camerascited by 1
  35. 2023Parcel3D: Shape Reconstruction from Single RGB Images for Applications in Transportation Logisticscited by 1
  36. 2023Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detectioncited by 1
  37. 2024False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracycited by 1
  38. 2024Temporal Enhanced Floating Car Observerscited by 1

50 most cited of 66 All 66 (JSON)