PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Wide-baseline stereo from multiple views : a probabilistic account
Christoph Strecha, Rik Fransens and Luc Van Gool
In: IEEE computer society conference on computer vision and pattern recognition, 27 June - 2 July, 2004, Washington, USA.


This paper describes a method for dense depth reconstruction from a small set of wide-baseline images. In a widebaseline setting an inherent difficulty which complicates the stereo-correspondence problem is self-occlusion. Also, we have to consider the possibility that image pixels in different images, which are projections of the same point in the scene, will have different color values due to non-Lambertian effects or discretization errors. We propose a Bayesian approach to tackle these problems. In this framework, the images are regarded as noisy measurements of an underlying ’true’ image-function. Also, the image data is considered incomplete, in the sense that we do not know which pixels from a particular image are occluded in the other images. We describe an EM-algorithm, which iterates between estimating values for all hidden quantities, and optimizing the current depth estimates. The algorithm has few free parameters, displays a stable convergence behavior and generates accurate depth estimates. The approach is illustrated with several challenging real-world examples. We also show how the algorithm can generate realistic view interpolations and how it merges the information of all images into a new, synthetic view.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:877
Deposited By:Rik Fransens
Deposited On:03 January 2005