The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...
In this paper, we present a novel algorithm for partial
intrinsic symmetry detection in 3D geometry. Unlike previous
work, our algorithm is based on a conceptually simple
and st...
Ruxandra Lasowski, Art Tevs, Hans-Peter Seidel, Mi...
Abstract. Traditional stereo algorithms implicitly use the frontal parallel plane assumption when exploiting contextual information, since the smoothness prior biases towards const...
Real-time applications with security requirements are emerging in various areas including government, education, and business. The security sensitive real-time applications can ta...
Many large-scale parallel programs follow a bulk synchronous parallel (BSP) structure with distinct computation and communication phases. Although the communication phase in such ...
Torsten Hoefler, Christian Siebert, Andrew Lumsdai...