A Stochastic Cost Function for Stereo Vision

Christian Unger and Slobodan Ilic

In Proceedings British Machine Vision Conference 2014


In this paper, we use random walks to infer information about the disparities in the image. While the random walks help to maintain sharp object boundaries, we introduce a correlation step that handles occlusions and slanted surfaces. The random walks are then used to build a stochastic cost function which serves to identify the most probable disparities. This also delivers valuable information about the reliability of the depths by exploiting their consistency statistically. Our method delivers very good results by means of local matching, but we also demonstrate that the obtained cost function is well suited for global optimization techniques. Moreover, our consistency maps deliver reliable statistical information about the confidence of disparity maps. In our paper we provide extensive evaluations with challenging images and show that our cost function based on random walks is very useful.


3D and Stereo


Extended Abstract (PDF, 1 page, 847K)
Paper (PDF, 11 pages, 2.5M)
Supplemental Materials (ZIP, 2.6M)
Bibtex File



Christian Unger, and Slobodan Ilic. A Stochastic Cost Function for Stereo Vision. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.


	title = {A Stochastic Cost Function for Stereo Vision},
	author = {Unger, Christian and Ilic, Slobodan},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.15 }