PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Fast visual hull and stereo matching on CUDA
Mykyta Fastovets, Jean-Yves Guillemaut and Adrian Hilton
In: CVMP 2009, 12-13 Nov 2009, London, United Kingdom.

Abstract

Stereo matching and visual hull are techniques that are often used in 3D reconstruction. This paper presents and evaluates implementations of these algorithms on the GPU using the CUDA architecture. Experimental results show that both, visual hull and stereo matching, have much to gain in terms of speed from the data parallel execution model.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Poster)
Additional Information:This short paper shows how GPU programming can be successfully used to greatly improve visual hull and stereo matching execution speeds.
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
Learning/Statistics & Optimisation
ID Code:5646
Deposited By:Mykyta Fastovets
Deposited On:08 March 2010