mlsanityData to 7 Oct 2026

On the uncertainty of self-supervised monocular depth estimation

arXiv 2005.06209 ↗First posted 13 May 2020cs.CVcited by 182

Not on the map. Why?

Abstract (arXiv)

Self-supervised paradigms for monocular depth estimation are very appealing since they do not require ground truth annotations at all. Despite the astonishing results yielded by such methodologies, learning to reason about the uncertainty of the estimated depth maps is of paramount importance for practical applications, yet uncharted in the literature. Purposely, we explore for the first time how to estimate the uncertainty for this task and how this affects depth accuracy, proposing a novel peculiar technique specifically designed for self-supervised approaches. On the standard KITTI dataset, we exhaustively assess the performance of each method with different self-supervised paradigms. Such evaluation highlights that our proposal i) always improves depth accuracy significantly and ii) yields state-of-the-art results concerning uncertainty estimation when training on sequences and competitive results uniquely deploying stereo pairs.

Key facts. Cited by 182 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 28; 2022: 35; 2023: 40; 2024: 27; 2025: 30; 2026: 22.

182 papers.

Sort:

By area:

  1. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 170
  2. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  3. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  4. 2021Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Mergingcited by 104
  5. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  6. 2024NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wildcited by 85
  7. 2022Conditional-Flow NeRF: Accurate 3D Modelling with Reliable Uncertainty Quantificationcited by 71
  8. 2021Unsupervised Scale-consistent Depth Learning from Videocited by 69
  9. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  10. 2023Robust Monocular Depth Estimation under Challenging Conditionscited by 58
  11. 2021Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimationcited by 55
  12. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
38 more
  1. 2021Learning Multiple Dense Prediction Tasks from Partially Annotated Datacited by 42
  2. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  3. 2021Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completioncited by 39
  4. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  5. 2022RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimationcited by 36
  6. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  7. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  8. 2023Self-supervised Monocular Depth Estimation: Let's Talk About The Weathercited by 33
  9. 2022Not Just Streaks: Towards Ground Truth for Single Image Derainingcited by 31
  10. 2024Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditionscited by 29
  11. 2021Unsupervised Monocular Depth Estimation in Highly Complex Environmentscited by 28
  12. 2023Atlantis: Enabling Underwater Depth Estimation with Stable Diffusioncited by 28
  13. 2022Sparsity Agnostic Depth Completioncited by 27
  14. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  15. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  16. 2022Monitored Distillation for Positive Congruent Depth Completioncited by 24
  17. 2021Bayesian Deep Basis Fitting for Depth Completion with Uncertaintycited by 23
  18. 2023Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimationcited by 23
  19. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  20. 2023RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenescited by 22
  21. 2023Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTVcited by 21
  22. 2023Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenescited by 20
  23. 2024RadarCam-Depth: Radar-Camera Fusion for Depth Estimation with Learned Metric Scalecited by 20
  24. 2025Toward Real-world BEV Perception: Depth Uncertainty Estimation via Gaussian Splattingcited by 20
  25. 2022Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsicscited by 19
  26. 2022Semantic-SuPer: A Semantic-aware Surgical Perception Framework for Endoscopic Tissue Identification, Reconstruction, and Trackingcited by 19
  27. 2023Symmetric Uncertainty-Aware Feature Transmission for Depth Super-Resolutioncited by 19
  28. 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
  29. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 19
  30. 2022Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Mattercited by 18
  31. 2024RankED: Addressing Imbalance and Uncertainty in Edge Detection Using Ranking-based Lossescited by 18
  32. 2021Stereoscopic Universal Perturbations across Different Architectures and Datasetscited by 17
  33. 2022Latent Discriminant deterministic Uncertaintycited by 17
  34. 2022Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimationcited by 17
  35. 2023LightDepth: Single-View Depth Self-Supervision from Illumination Declinecited by 17
  36. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 17
  37. 2024MVG-Splatting: Multi-View Guided Gaussian Splatting with Adaptive Quantile-Based Geometric Consistency Densificationcited by 16
  38. 2023AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimationcited by 15

50 most cited of 182 All 182 (JSON)