We are building a system that can automatically acquire 3D range scans and 2D images to build geometrically and photometrically correct 3D models of urban environments. A major bo...
We present a new method for matching line segments between two uncalibrated wide-baseline images. Most current techniques for wide-baseline matching are based on viewpoint invaria...
This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
This paper proposes a technique for estimating piecewise planar models of objects from their images and geometric constraints. First, assuming a bounded noise in the localization ...
In this paper, we present an approach for monitoring the positions of vector field singularities in time-dependent datasets. The concept of singularity index is discussed and exte...
Christoph Garth, Xavier Tricoche, Gerik Scheuerman...