Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids
- 1 June 2016
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
- p. 4706-4714
- https://doi.org/10.1109/cvpr.2016.509
Abstract
We present a global optimization approach to optical flow estimation. The approach optimizes a classical optical flow objective over the full space of mappings between discrete grids. No descriptor matching is used. The highly regular structure of the space of mappings enables optimizations that reduce the computational complexity of the algorithm's inner loop from quadratic to linear and support efficient matching of tens of thousands of nodes to tens of thousands of displacements. We show that one-shot global optimization of a classical Horn-Schunck-type objective over regular grids at a single resolution is sufficient to initialize continuous interpolation and achieve state-of-the-art performance on challenging modern benchmarks.Keywords
This publication has 37 references indexed in Scilit:
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Global minimization of Markov random fields with applications to optical flowInverse Problems & Imaging, 2012
- Honeybees as a Model for the Study of Visually Guided Flight, Navigation, and Biologically Inspired RoboticsPhysiological Reviews, 2011
- Efficient MRF deformation model for non-rigid image matchingComputer Vision and Image Understanding, 2008
- MAP Estimation Via Agreement on Trees: Message-Passing and Linear ProgrammingIEEE Transactions on Information Theory, 2005
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- Multimodal estimation of discontinuous optical flow using Markov random fieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Sequence comparison with mixed convex and concave costsJournal of Algorithms, 1990
- Geometric applications of a matrix-searching algorithmAlgorithmica, 1987
- Determining optical flowArtificial Intelligence, 1981