Using One Graph-Cut to Fuse Multiple Candidate Maps in Depth Estimation

Graph-cut techniques for depth and disparity estimations are known to be powerful but also slow. We propose a graph-cut framework that is able to estimate depth maps from a set of candidate values. By employing a restricted set of candidates for each pixel, rough depth maps can be effectively refine...

Ausführliche Beschreibung

Bibliographische Detailangaben

1. Verfasser:	Pitie, F.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Bayesian methods Belief propagation candidate selection disparity estimation Educational institutions Fuses graph-cut Labeling Markov random fields Message passing Production Simulated annealing Tree graphs
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!