mlsanityData to 7 Oct 2026

Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow

arXiv 1802.07095 ↗First posted 20 Feb 2018cs.CVcited by 135

Not on the map. Why?

Abstract (arXiv)

Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative methodology. In this paper, we make such networks estimate their local uncertainty about the correctness of their prediction, which is vital information when building decisions on top of the estimations. For the first time we compare several strategies and techniques to estimate uncertainty in a large-scale computer vision task like optical flow estimation. Moreover, we introduce a new network architecture utilizing the Winner-Takes-All loss and show that this can provide complementary hypotheses and uncertainty estimates efficiently with a single forward pass and without the need for sampling or ensembles. Finally, we demonstrate the quality of the different uncertainty estimates, which is clearly above previous confidence measures on optical flow and allows for interactive frame rates.

Key facts. Cited by 135 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 23; 2023: 31; 2024: 17; 2025: 18; 2026: 25.

135 papers.

Sort:

By area:

  1. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  2. 2021Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimationcited by 116
  3. 2021Learning Accurate Dense Correspondences and When to Trust Themcited by 113
  4. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  5. 2023Bayes' Rays: Uncertainty Quantification for Neural Radiance Fieldscited by 90
  6. 2021PDC-Net+: Enhanced Probabilistic Dense Correspondence Networkcited by 80
  7. 2023MFT: Long-Term Tracking of Every Pixelcited by 61
  8. 2022Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equationscited by 59
  9. 2023A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyondcited by 55
  10. 2021Learning to Segment Rigid Motions from Two Framescited by 45
  11. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 44
  12. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 38
38 more
  1. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  2. 2023Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorialcited by 27
  3. 2022Gradient-based Uncertainty for Monocular Depth Estimationcited by 26
  4. 2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
  5. 2021Bayesian Deep Basis Fitting for Depth Completion with Uncertaintycited by 23
  6. 2023Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimationcited by 23
  7. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  8. 2022Learning Probabilistic Topological Representations Using Discrete Morse Theorycited by 20
  9. 2025POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimalitycited by 18
  10. 2022Latent Discriminant deterministic Uncertaintycited by 17
  11. 2024Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimationcited by 17
  12. 2024Uncertainty Quantification Metrics for Deep Regressioncited by 16
  13. 2025GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstructioncited by 15
  14. 2023How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?cited by 14
  15. 2023Bayesian Deep Learning for Affordance Segmentation in imagescited by 13
  16. 2023Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivitycited by 13
  17. 2021SLURP: Side Learning Uncertainty for Regression Problemscited by 12
  18. 2023Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysiscited by 12
  19. 2024QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challengecited by 12
  20. 2024Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealingcited by 12
  21. 2024Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splattingcited by 12
  22. 2021Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoringcited by 11
  23. 2023Pixel-wise Gradient Uncertainty for Convolutional Neural Networks applied to Out-of-Distribution Segmentationcited by 11
  24. 2024Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understandingcited by 11
  25. 2022Unsupervised confidence for LiDAR depth maps and applicationscited by 10
  26. 2022MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillationcited by 10
  27. 2023On the Calibration of Human Pose Estimationcited by 10
  28. 2021Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertaintycited by 9
  29. 2023A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimationcited by 9
  30. 2024Sources of Uncertainty in 3D Scene Reconstructioncited by 9
  31. 2021See Yourself in Others: Attending Multiple Tasks for Own Failure Detectioncited by 8
  32. 2022PeSOTIF: a Challenging Visual Dataset for Perception SOTIF Problems in Long-tail Traffic Scenarioscited by 8
  33. 2021SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimationcited by 7
  34. 2021On the Uncertain Single-View Depths in Colonoscopiescited by 6
  35. 2023MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertaintycited by 6
  36. 2024Regularized Multi-Decoder Ensemble for an Error-Aware Scene Representation Networkcited by 6
  37. 2025Zero-shot Depth Completion via Test-time Alignment with Affine-invariant Depth Priorcited by 6
  38. 2022Uncertainty-Aware Self-supervised Neural Network for Liver T1ρ Mapping with Relaxation Constraintcited by 5

50 most cited of 135 All 135 (JSON)