In this paper we introduce Bezier Lights, an intelligent lighting system that allows users to intuitively establish virtual boundaries in indoor environments. Boundaries can be ea...
Principal component analysis has proven to be useful for understanding geometric variability in populations of parameterized objects. The statistical framework is well understood ...
SIFT has been proven to be the most robust local invariant feature descriptor. SIFT is designed mainly for gray images. However, color provides valuable information in object desc...
We present a new algorithm to detect humans in still images utilizing covariance matrices as object descriptors. Since these descriptors do not lie on a vector space, well known m...
We propose a spatially continuous formulation of Ishikawa's discrete multi-label problem. We show that the resulting non-convex variational problem can be reformulated as a co...
Thomas Pock, Thomas Schoenemann, Gottfried Graber,...