We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked on...
This paper presents a novel method for surface recovery from discrete 3D point data sets. In order to produce improved reconstruction results, the algorithm presented in this paper...
—Representing 2D and 3D data sets with implicit polynomials (IPs) has been attractive because of its applicability to various computer vision issues. Therefore, many IP fitting m...
Abstract. We propose a shape descriptor for 3D ear impressions, derived from a comprehensive set of anatomical features. Motivated by hearing aid (HA) manufacturing, the selection ...
We present a novel approach to fluid simulation, allowing us to take into account the surface energy in a precise manner. This new approach combines a novel, topology-adaptive app...
Marek Krzysztof Misztal, Robert Bridson, Kenny Erl...