Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
This paper presents a new method for constructing compact statistical point-based models of ensembles of similar shapes that does not rely on any specific surface parameterization....
Joshua E. Cates, P. Thomas Fletcher, Martin Andrea...
Abstract. Shape retrieval/matching is a very important topic in computer vision. The recent progress in this domain has been mostly driven by designing smart features for providing...
Xingwei Yang, Xiang Bai, Longin Jan Latecki, Zhuow...
Abstract. We present a novel method for the segmentation of volumetric images, which is especially suitable for highly variable soft tissue structures. Core of the algorithm is a s...
—This paper introduces paper-strip sculptures, a physical mesh data-structure used to represent 2manifold mesh surfaces for understanding topological and geometrical aspects of s...