Header logo is

Discrete Optimization for Optical Flow


Conference Paper



We propose to look at large-displacement optical flow from a discrete point of view. Motivated by the observation that sub-pixel accuracy is easily obtained given pixel-accurate optical flow, we conjecture that computing the integral part is the hardest piece of the problem. Consequently, we formulate optical flow estimation as a discrete inference problem in a conditional random field, followed by sub-pixel refinement. Naive discretization of the 2D flow space, however, is intractable due to the resulting size of the label set. In this paper, we therefore investigate three different strategies, each able to reduce computation and memory demands by several orders of magnitude. Their combination allows us to estimate large-displacement optical flow both accurately and efficiently and demonstrates the potential of discrete optimization for optical flow. We obtain state-of-the-art performance on MPI Sintel and KITTI.

Author(s): Moritz Menze and Christian Heipke and Andreas Geiger
Book Title: German Conference on Pattern Recognition (GCPR)
Volume: 9358
Pages: 16--28
Year: 2015
Publisher: Springer International Publishing

Department(s): Autonomous Vision, Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

DOI: 10.1007/978-3-319-24947-6_2
Event Place: Aachen

ISBN: 978-3-319-24946-9

Links: pdf


  title = {Discrete Optimization for Optical Flow},
  author = {Menze, Moritz and Heipke, Christian and Geiger, Andreas},
  booktitle = {German Conference on Pattern Recognition (GCPR)},
  volume = {9358},
  pages = {16--28},
  publisher = {Springer International Publishing},
  year = {2015}