WxBS: Wide Baseline Stereo Generalizations

Dmytro Mishkin, Jiri Matas, Michal Perdoch and Karel Lenc

Abstract

We present a generalization of the wide baseline two view matching problem - WxBS, where x stands for a different subset of 'wide baselines' in acquisition conditions such as geometry, illumination, sensor and appearance. We introduce a novel dataset of ground-truthed image pairs which include multiple 'wide baselines' and show that state-of-the-art matchers fail on almost all image pairs from the set. A novel matching algorithm for addressing the WxBS problem is introduced and we show experimentally that the WxBS-M matcher dominates the state-of-the-art methods both on the new and existing datasets.

Session

Poster 1

Files

PDF iconExtended Abstract (PDF, 890K)
PDF iconPaper (PDF, 8M)
ZIP iconSupplemental Materials (ZIP, 19M)

DOI

10.5244/C.29.12
https://dx.doi.org/10.5244/C.29.12

Citation

Dmytro Mishkin, Jiri Matas, Michal Perdoch and Karel Lenc. WxBS: Wide Baseline Stereo Generalizations. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 12.1-12.12. BMVA Press, September 2015.

Bibtex

@inproceedings{BMVC2015_12,
	title={WxBS: Wide Baseline Stereo Generalizations},
	author={Dmytro Mishkin and Jiri Matas and Michal Perdoch and Karel Lenc},
	year={2015},
	month={September},
	pages={12.1-12.12},
	articleno={12},
	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.29.12},
	isbn={1-901725-53-7},
	url={https://dx.doi.org/10.5244/C.29.12}
}