Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Energy minimization of discrete functions with higher-order potentials for depth map generation

: Bulatov, Dimitri; Kottler, Benedikt; Rottensteiner, Franz

Fulltext urn:nbn:de:0011-n-4265739 (3.3 MByte PDF)
MD5 Fingerprint: ffa4417def41cfd65835c39022e74077
Created on: 3.1.2017

Institute of Electrical and Electronics Engineers -IEEE-:
23rd International Conference on Pattern Recognition, ICPR 2016 : Cancun, Mexico, December 4-8, 2016
Piscataway, NJ: IEEE, 2016
ISBN: 978-1-5090-4846-5
ISBN: 978-1-5090-4847-2
ISBN: 978-1-5090-4848-9
International Conference on Pattern Recognition (ICPR) <23, 2016, Cancun>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Minimization of discrete energy functions considering higher-order potentials is a challenging yet an important problem. In this work, a three-step procedure will be presented and exemplified on a general problem related to the dense depth map computation from multi-view configurations: Achieving a joint reconstruction of structure and semantics with piecewise planarity constraints. The three steps of the procedure are binarization, quadratization, and energy minimization. While the first and the third step are accomplished using procedures based on alpha-expansion and max-flow algorithms, respectively, we propose for the quadratization step a fast and simple module to reformulate the higher-order problem as a quadratic one. This module is based on edge statistics and is particularly useful for regular graphs and for third- or fourth-order potentials.