mlsanityData to 7 Oct 2026

Unsupervised Learning of Depth and Ego-Motion from Video

arXiv 1704.07813 ↗First posted 25 Apr 2017cs.CVcited by 778

Not on the map. Why?

Abstract (arXiv)

We present an unsupervised learning framework for the task of monocular depth and camera motion estimation from unstructured video sequences. We achieve this by simultaneously training depth and camera pose estimation networks using the task of view synthesis as the supervisory signal. The networks are thus coupled via the view synthesis objective during training, but can be applied independently at test time. Empirical evaluation on the KITTI dataset demonstrates the effectiveness of our approach: 1) monocular depth performing comparably with supervised methods that use either ground-truth pose or depth for training, and 2) pose estimation performing favorably with established SLAM systems under comparable input settings.

Key facts. Cited by 778 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 180; 2022: 176; 2023: 149; 2024: 129; 2025: 88; 2026: 56.

778 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  4. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  5. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  6. 2022Cross-view Transformers for real-time Map-view Semantic Segmentationcited by 264
  7. 2021Is Pseudo-Lidar needed for Monocular 3D Object detection?cited by 248
  8. 2023A Cookbook of Self-Supervised Learningcited by 248
  9. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  10. 2023Visual Geometry Grounded Deep Structure From Motioncited by 225
  11. 2023Robust Dynamic Radiance Fieldscited by 193
  12. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
38 more
  1. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  2. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 190
  3. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  4. 2022Depth-Aware Generative Adversarial Network for Talking Head Video Generationcited by 177
  5. 2022HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentationcited by 163
  6. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  7. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 146
  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. 2021Unidentified Video Objects: A Benchmark for Dense, Open-World Segmentationcited by 133
  12. 2023SelfOcc: Self-Supervised Vision-Based 3D Occupancy Predictioncited by 133
  13. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  14. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  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. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  19. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited 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. 2023Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysiscited by 99
  24. 2025Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Controlcited by 95
  25. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  26. 2021UniFuse: Unidirectional Fusion for 360circ Panorama Depth Estimationcited by 91
  27. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  28. 2021Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraintscited by 80
  29. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  30. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  31. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 74
  32. 2023Detector-Free Structure from Motioncited by 71
  33. 2021Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescuecited by 70
  34. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  35. 2021Monocular 3D Object Detection: An Extrinsic Parameter Free Approachcited by 69
  36. 2021Deep Regression on Manifolds: A 3D Rotation Case Studycited by 67
  37. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  38. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66

50 most cited of 778 All 778 (JSON)