Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement
Daniel Maurer, Michael Stoll and Andres Bruhn
Abstract
Variational approaches form an inherent part of most state-of-the-art pipeline approaches for optical flow computation. As the final step of the pipeline, the aim is to
refine an initial flow field typically obtained by inpainting non-dense matches in order
to provide highly accurate results. In this paper, we take advantage of recent improvements in variational optical flow estimation to construct an advanced variational model
for this final refinement step. By combining an illumination aware data term with an order adaptive smoothness term, we obtain a highly flexible model that is able to cope well
with a broad variety of different scenarios. Moreover, we propose the use of an additional reduced coarse-to-fine scheme instead of an exclusive initialisation scheme, which
not only allows to refine the initialisation but also allows to correct larger erroneous
displacements. Experiments on recent optical flow benchmarks show the advantages of
the advanced variational refinement and the reduced coarse to fine scheme.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.150
https://dx.doi.org/10.5244/C.31.150
Citation
Daniel Maurer, Michael Stoll and Andres Bruhn. Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 150.1-150.13. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_150,
title={Order-Adaptive and Illumination-Aware Variational Optical Flow Refinement},
author={Daniel Maurer, Michael Stoll and Andres Bruhn},
year={2017},
month={September},
pages={150.1-150.13},
articleno={150},
numpages={13},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.150},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.150}
}