Learn More
The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern(More)
[1] Recent theoretical and empirical studies show that the generalization ability of artificial neural networks can be improved by combining several artificial neural networks in redundant ensembles. In this paper, a review is given of popular ensemble methods. Six approaches for creating artificial neural network ensembles are applied in pooled flood(More)
When reconstructing a specific type or class of object using stereo, we can leverage prior knowledge of the shape of that type of object. A popular class of object to reconstruct is the human face. In this paper we learn a statistical wavelet prior of the shape of the human face and use it to constrain stereo reconstruction within a Bayesian framework. We(More)
Non-rigid shape matching is one of the most challenging fields in content-based 3D object retrieval. The aim of the SHREC 2010-Shape Retrieval Contest of Non-rigid 3D Models is to evaluate and compare the effectiveness of different methods run on a non-rigid 3D shape benchmark consisting of 200 watertight triangular meshes. Three groups with six methods(More)
We present an algorithm for automatic locating of anthropometric landmarks on 3D human scans. Our method is based on learning landmark characteristics and the spatial relationships between them from a set of human scans where the landmarks are identified. The learned information is formulated by a pairwise Markov network. Each node of the network is a(More)
Communicated by (xxxxxxxxxx) We present an approach to find dense point-to-point correspondences between two deformed surfaces corresponding to different postures of the same non-rigid object in a fully automatic way. The approach requires no prior knowledge about the shapes being registered or the initial alignment of the shapes. We consider surfaces that(More)
Permission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such material is fully acknowledged. Abstract Characterizing the variations of the human body shape is fundamentally important in many applications ranging from animation to product design. 3D scanning technology makes it possible(More)
This paper describes a technique for finding regular grids in the images of calibration patterns, a crucial step in calibrating cameras. Corner features located by a corner detector are connected using Delaunay triangulation. Pairs of neighboring triangles are combined into quadrilaterals, which are then topolog-ically filtered and ordered. We introduce a(More)