# Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow

arXiv: https://arxiv.org/abs/1802.07095 · HTML: https://mlsanity.com/paper/1802.07095/

## Key facts

- Cited by 135 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2018.

## Built on by (most cited first, 30 of 135)

- [ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer](https://mlsanity.com/paper/2208.14201/) (2022)
- [Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation](https://mlsanity.com/paper/2109.09881/) (2021)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging](https://mlsanity.com/paper/2202.05265/) (2022)
- [Bayes' Rays: Uncertainty Quantification for Neural Radiance Fields](https://mlsanity.com/paper/2309.03185/) (2023)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [MFT: Long-Term Tracking of Every Pixel](https://mlsanity.com/paper/2305.12998/) (2023)
- [Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations](https://mlsanity.com/paper/2206.08311/) (2022)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [RoMa v2: Harder Better Faster Denser Feature Matching](https://mlsanity.com/paper/2511.15706/) (2025)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)
- [A Benchmark and a Baseline for Robust Multi-view Depth Estimation](https://mlsanity.com/paper/2209.06681/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial](https://mlsanity.com/paper/2305.04933/) (2023)
- [Gradient-based Uncertainty for Monocular Depth Estimation](https://mlsanity.com/paper/2208.02005/) (2022)
- [MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks](https://mlsanity.com/paper/2203.01437/) (2022)
- [Bayesian Deep Basis Fitting for Depth Completion with Uncertainty](https://mlsanity.com/paper/2103.15254/) (2021)
- [Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation](https://mlsanity.com/paper/2304.00152/) (2023)
- [Representation Uncertainty in Self-Supervised Learning as Variational Inference](https://mlsanity.com/paper/2203.11437/) (2022)
- [Learning Probabilistic Topological Representations Using Discrete Morse Theory](https://mlsanity.com/paper/2206.01742/) (2022)
- [Diffusion Model Guided Sampling with Pixel-Wise Aleatoric Uncertainty Estimation](https://mlsanity.com/paper/2412.00205/) (2024)
- [POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality](https://mlsanity.com/paper/2503.07819/) (2025)
- [Latent Discriminant deterministic Uncertainty](https://mlsanity.com/paper/2207.10130/) (2022)
- [GauSS-MI: Gaussian Splatting Shannon Mutual Information for Active 3D Reconstruction](https://mlsanity.com/paper/2504.21067/) (2025)
- [Uncertainty Quantification Metrics for Deep Regression](https://mlsanity.com/paper/2405.04278/) (2024)
- [How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?](https://mlsanity.com/paper/2302.03679/) (2023)
- [Bayesian Deep Learning for Affordance Segmentation in images](https://mlsanity.com/paper/2303.00871/) (2023)
- [Calibration in Machine Learning Uncertainty Quantification: beyond consistency to target adaptivity](https://mlsanity.com/paper/2309.06240/) (2023)
- [QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge](https://mlsanity.com/paper/2405.18435/) (2024)
- [SLURP: Side Learning Uncertainty for Regression Problems](https://mlsanity.com/paper/2110.11182/) (2021)

## 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.