mlsanityData to 7 Oct 2026

Unsupervised Monocular Depth Estimation with Left-Right Consistency

arXiv 1609.03677 ↗First posted 13 Sep 2016cs.CV cs.LG stat.MLcited by 819

Not on the map. Why?

Abstract (arXiv)

Learning based methods have shown very promising results for the task of depth estimation in single images. However, most existing approaches treat depth prediction as a supervised regression problem and as a result, require vast quantities of corresponding ground truth depth data for training. Just recording quality depth data in a range of environments is a challenging problem. In this paper, we innovate beyond existing approaches, replacing the use of explicit depth data during training with easier-to-obtain binocular stereo footage. We propose a novel training objective that enables our convolutional neural network to learn to perform single image depth estimation, despite the absence of ground truth depth data. Exploiting epipolar geometry constraints, we generate disparity images by training our network with an image reconstruction loss. We show that solving for image reconstruction alone results in poor quality depth images. To overcome this problem, we propose a novel training loss that enforces consistency between the disparities produced relative to both the left and right images, leading to improved performance and robustness compared to existing approaches. Our method produces state of the art results for monocular depth estimation on the KITTI driving dataset, even outperforming supervised methods that have been trained with ground truth depth.

Key facts. Cited by 819 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 207; 2022: 184; 2023: 145; 2024: 129; 2025: 98; 2026: 56.

819 papers.

Sort:

By area:

  1. 2021Vision Transformers for Dense Predictioncited by 1,789
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  4. 2021Neural RGB-D Surface Reconstructioncited by 312
  5. 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
  6. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  7. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  8. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  9. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  10. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  11. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  12. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
38 more
  1. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  2. 2022BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimationcited by 166
  3. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  4. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  5. 2022NOTE: Robust Continual Test-time Adaptation Against Temporal Correlationcited by 150
  6. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 139
  7. 2021Delving into Localization Errors for Monocular 3D Object Detectioncited by 138
  8. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  9. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  10. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  11. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  12. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  13. 2023DiffusioNeRF: Regularizing Neural Radiance Fields with Denoising Diffusion Modelscited by 127
  14. 2022DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimationcited by 116
  15. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  16. 2022Map-free Visual Relocalization: Metric Pose Relative to a Single Imagecited by 112
  17. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  18. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  19. 20243D Gaussian as a New Era: A Surveycited by 102
  20. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  21. 2023Towards Zero-Shot Scale-Aware Monocular Depth Estimationcited by 100
  22. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  23. 2022Deep Image Deblurring: A Surveycited by 94
  24. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  25. 2022Attention Attention Everywhere: Monocular Depth Prediction with Skip Attentioncited by 92
  26. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  27. 2023Monocular Depth Estimation using Diffusion Modelscited by 87
  28. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 85
  29. 2021Weakly Supervised Object Localization and Detection: A Surveycited by 84
  30. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  31. 2021VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehiclescited by 81
  32. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  33. 2021Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraintscited by 80
  34. 2021DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentationcited by 80
  35. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  36. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  37. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  38. 2024Restoring Images in Adverse Weather Conditions via Histogram Transformercited by 73

50 most cited of 819 All 819 (JSON)