Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
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.
Code (1)
Tasks
Optical Flow EstimationSimilar Papers 제목 키워드 기반
Bayesian Optical Flow with Uncertainty Quantification
Optical flow refers to the visual motion observed between two consecutive images. Since the degree of freedom is typically much larger than the constraints imposed by the image observations, the straightforward formulati…
Optical Flow EstimationUncertainty QuantificationU$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation
Unsupervised optical flow methods typically lack reliable uncertainty estimation, limiting their robustness and interpretability. We propose U$^{2}$Flow, the first recurrent unsupervised framework that jointly estimates …
Optical Flow EstimationJoint Self-supervised Depth and Optical Flow Estimation towards Dynamic Objects
Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, in…
Depth EstimationMotion SegmentationOptical Flow EstimationSSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation
Inaccurate optical flow estimates in and near occluded regions, and out-of-boundary regions are two of the current significant limitations of optical flow estimation algorithms. Recent state-of-the-art optical flow estim…
Optical Flow EstimationThe Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation
Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without …
DenoisingDepth EstimationDiversityImage Generation+3