PhD Defense

Multi-View Stereo as an Inverse Inference Problem

Christoph Strecha

Defense

When? Tuesday, May 22nd, 2007 at 2 pm
Where? Auditorium A, Department of Electrical Engineering - ESAT, Kasteelpark Arenberg 10, 3001 Leuven, Belgium (map)
Duration? defense: approximately two hours, reception: afterwards
Language? English (slides: English)

Promoter:
Prof. Luc Van Gool, Faculteit Toegepaste Wetenschappen, Dept. ESAT, PSI-VISICS, K.U. Leuven

Jury:
Prof. A. Bultheel, chairman (K.U.Leuven)
Prof. L. Van Gool, promoter (K.U.Leuven)
Prof. P. Sturm, assessor (INRIA France)
Prof. M. Jansen, assessor (K.U.Leuven)
Prof. D. Vandermeulen, assessor (K.U.Leuven)
Prof. L. Van Eycken, assessor (K.U.Leuven)
Prof. P. Wambacq, assessor (K.U.Leuven)

Abstract

This thesis deals with the dense multi-view stereo problem. The inherent difficulties which complicate the stereo-correspondence problem are occlusions. Also, we have to consider the po ssibility that image pixels in different images, which are projections of the same point in the scene, will have different colour values due to non-Lambertian effects or discretisation errors. To tackle these problems we propose a generative model based approach. In this approach, 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 w hich pixels from a particular image are occluded in the other images. This formulation is equivalent to an inverse inference problem, where the goal is to estimate the factors that have generated the input images. More particular, given a set of images from a scene, we consider the question what would be the most likely image that would have been observed from a particular camera position. To answer this question, we study a global and a local formulation. In a global formulation all possible geometric realisations of a scene are considered and evaluated to find the most plausible realisation. The local formulation takes an initial geometric realisation and refines it in a gradient decent manner. Both formulations are intensely evaluated and their advantages and disadvantages are discussed. Finally, our proposed multi-view stereo algorithm combines both formulations and its perf ormance is illustrated on several real-world examples. We show how the algorithm can generate realistic view interpolations from a virtual camera viewpoint.

Contact Information

Christoph Strecha
Department ESAT, PSI-VISICS
Katholieke Universiteit Leuven
Kasteelpark Arenberg 10
B-3001 Leuven-Heverlee, Belgium

Tel. 016/32.1079
E-mail: Christoph.Strecha@esat.kuleuven.be
Web: http://www.esat.kuleuven.ac.be/~cstrecha
Fotos: fotos