caa a22 4500 467914621 CHVBK 20180406152858.0 cr unu---uuuuu 170328e20061001xx s 000 0 eng 10.1007/s11263-006-7899-4 doi (NATIONALLICENCE)springer-10.1007/s11263-006-7899-4 Efficient Belief Propagation for Early Vision [Elektronische Daten] [Pedro Felzenszwalb, Daniel Huttenlocher] Markov random field models provide a robust and unified framework for early vision problems such as stereo and image restoration. Inference algorithms based on graph cuts and belief propagation have been found to yield accurate results, but despite recent advances are often too slow for practical use. In this paper we present some algorithmic techniques that substantially improve the running time of the loopy belief propagation approach. One of the techniques reduces the complexity of the inference algorithm to be linear rather than quadratic in the number of possible labels for each pixel, which is important for problems such as image restoration that have a large label set. Another technique speeds up and reduces the memory requirements of belief propagation on grid graphs. A third technique is a multi-grid method that makes it possible to obtain good results with a small fixed number of message passing iterations, independent of the size of the input images. Taken together these techniques speed up the standard algorithm by several orders of magnitude. In practice we obtain results that are as accurate as those of other global methods (e.g., using the Middlebury stereo benchmark) while being nearly as fast as purely local methods. Springer Science + Business Media, LLC, 2006 belief propagation nationallicence Markov random fields nationallicence stereo nationallicence image restoration nationallicence efficient algorithms nationallicence Felzenszwalb Pedro Computer Science Department, University of Chicago, Chicago aut Huttenlocher Daniel Computer Science Department, Cornell University, USA aut International Journal of Computer Vision Kluwer Academic Publishers 70/1(2006-10-01), 41-54 0920-5691 70:1<41 2006 70 11263 https://doi.org/10.1007/s11263-006-7899-4 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-006-7899-4 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Felzenszwalb Pedro Computer Science Department, University of Chicago, Chicago aut NATIONALLICENCE 700 1- Huttenlocher Daniel Computer Science Department, Cornell University, USA aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 70/1(2006-10-01), 41-54 0920-5691 70:1<41 2006 70 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer