Home
Uni-Logo
 

Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow

European Conference on Computer Vision (ECCV), 2018
Abstract: 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 and loss function that enforce complementary hypotheses and provide uncertainty estimates efficiently with a single forward pass and without the need for sampling or ensembles. We demonstrate the quality of the uncertainty estimates, which is clearly above previous confidence measures on optical flow and allows for interactive frame rates.
Paper Poster

Images and movies

 

BibTex reference

@InProceedings{ICKMB18,
  author       = "E. Ilg and {\"O}. {\c{C}}i{\c{c}}ek and S. Galesso and A. Klein and O. Makansi and F. Hutter and T. Brox",
  title        = "Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow",
  booktitle    = "European Conference on Computer Vision (ECCV)",
  month        = " ",
  year         = "2018",
  note         = "https://arxiv.org/abs/1802.07095",
  url          = "http://lmb.informatik.uni-freiburg.de/Publications/2018/ICKMB18"
}

Other publications in the database