mlsanityData to 7 Oct 2026

Unsupervised Monocular Depth Learning in Dynamic Scenes

arXiv 2010.16404 ↗First posted 30 Oct 2020cs.CV cs.GR cs.LGcited by 84

Not on the map. Why?

Abstract (arXiv)

We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including methods that require semantic input. Code is at https://github.com/google-research/google-research/tree/master/depth_and_motion_learning .

Key facts. Cited by 84 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 15; 2023: 23; 2024: 22; 2025: 3; 2026: 6.

84 papers.

Sort:

By area:

  1. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  2. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 92
  3. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  4. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  5. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  6. 2022SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenescited by 50
  7. 2021Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Predictioncited by 48
  8. 2022Disentangling Object Motion and Occlusion for Unsupervised Multi-frame Monocular Depthcited by 48
  9. 2021R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenescited by 36
  10. 2024Cross-View Completion Models are Zero-shot Correspondence Estimatorscited by 30
  11. 2022(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answeringcited by 29
  12. 2023Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenescited by 25
38 more
  1. 2021Attentive and Contrastive Learning for Joint Depth and Motion Field Estimationcited by 24
  2. 2022When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimationcited by 24
  3. 2023RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenescited by 22
  4. 2023SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimationcited by 21
  5. 2022Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problemcited by 20
  6. 2023Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenescited by 20
  7. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 18
  8. 2023CoDEPS: Online Continual Learning for Depth Estimation and Panoptic Segmentationcited by 18
  9. 2023DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibriumcited by 16
  10. 2023Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Networkcited by 14
  11. 2024RoDUS: Robust Decomposition of Static and Dynamic Elements in Urban Scenescited by 14
  12. 2022The Monocular Depth Estimation Challengecited by 13
  13. 2023From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Priorcited by 13
  14. 2024SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Imagescited by 13
  15. 2022Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learningcited by 12
  16. 2023Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenescited by 12
  17. 2024DCPI-Depth: Explicitly Infusing Dense Correspondence Prior to Unsupervised Monocular Depth Estimationcited by 12
  18. 20213D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Videocited by 11
  19. 2021Dimensions of Motion: Monocular Prediction through Flow Subspacescited by 10
  20. 2022MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Posecited by 10
  21. 2024Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimationcited by 9
  22. 2021Self-Supervised Monocular Scene Decomposition and Depth Estimationcited by 8
  23. 2023DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volumecited by 8
  24. 2023Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimationcited by 8
  25. 2024SPIdepth: Strengthened Pose Information for Self-supervised Monocular Depth Estimationcited by 8
  26. 2021ColDE: A Depth Estimation Framework for Colonoscopy Reconstructioncited by 7
  27. 2023Deeper into Self-Supervised Monocular Indoor Depth Estimationcited by 7
  28. 2024Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenescited by 7
  29. 2021Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structurecited by 6
  30. 2024ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusioncited by 6
  31. 2023Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimationcited by 4
  32. 2024MAL: Motion-Aware Loss with Temporal and Distillation Hints for Self-Supervised Depth Estimationcited by 4
  33. 2024Self-Supervised Monocular Depth Estimation in the Dark: Towards Data Distribution Compensationcited by 4
  34. 2024MambaDepth: Enhancing Long-range Dependency for Self-Supervised Fine-Structured Monocular Depth Estimationcited by 4
  35. 2023PPEA-Depth: Progressive Parameter-Efficient Adaptation for Self-Supervised Monocular Depth Estimationcited by 3
  36. 2024The Devil is in the Edges: Monocular Depth Estimation with Edge-aware Consistency Fusioncited by 3
  37. 2024Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimationcited by 3
  38. 2024On-Device Self-Supervised Learning of Low-Latency Monocular Depth from Only Eventscited by 3

50 most cited of 84 All 84 (JSON)