Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation
Benjamin Drayer and Thomas Brox
Abstract
One fundamental step in many state of the art optical flow methods is the initial estimation of reliable correspondences. It is well-established to extract and match features such as HOG to handle large displacements. We propose a combinatorial refinement of the initial matching. The (generally) sparse correspondences serve as a cue for our dense estimation. Optimization is done in the space of affine motion, where we regularize between neighboring points and similar regions. The evaluation on the MPI-Sintel dataset shows that the proposed method removes outliers from the initial matching and increases the number of reliable matches. The proposed refinement improves all optical flow algorithms that build upon pre-computed correspondences.
Session
Poster 1
Files
Extended Abstract (PDF, 4M)
Paper (PDF, 8M)
DOI
10.5244/C.29.42
https://dx.doi.org/10.5244/C.29.42
Citation
Benjamin Drayer and Thomas Brox. Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 42.1-42.12. BMVA Press, September 2015.
Bibtex
@inproceedings{BMVC2015_42,
title={Combinatorial Regularization of Descriptor Matching for Optical Flow Estimation},
author={Benjamin Drayer and Thomas Brox},
year={2015},
month={September},
pages={42.1-42.12},
articleno={42},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
doi={10.5244/C.29.42},
isbn={1-901725-53-7},
url={https://dx.doi.org/10.5244/C.29.42}
}