PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Multi-view stereo via volumetric graph cuts
George Vogiatzis, Philip Torr and Roberto Cipolla
In: CVPR 2005, 20-25 June 2005, San Diego, USA.


This paper presents a novel formulation for the multiview scene reconstruction problem. While this formulation benefits from a volumetric scene representation, it is amenable to a computationally tractable global optimisation using Graph-cuts. The algorithm proposed uses the visual hull of the scene to infer occlusions and as a constraint on the topology of the scene. A photo consistencybased surface cost functional is defined and discretised with a weighted graph. The optimal surface under this discretised functional is obtained as the minimum cut solution of the weighted graph. Our method provides a viewpoint independent surface regularisation, approximate handling of occlusions and a tractable optimisation scheme. Promising experimental results on real scenes as well as a quantitative evaluation on a synthetic scene are presented.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Conference or Workshop Item (Oral)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:2823
Deposited By:Mudigonda Pawan Kumar
Deposited On:22 November 2006