We describe an effective and novel approach to infer sign and direction of principal curvatures at each input site from noisy 3D data. Unlike most previous approaches, no local su...
The aim of this paper is to achieve seamless image stitching without producing visual artifact caused by severe intensity discrepancy and structure misalignment, given that the inp...
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
In this paper, we develop methods to rapidly remove rough features from irregularly triangulated data intended to portray a smooth surface. The main task is to remove undesirable ...
Abstract In this paper, we present a segmentation algorithm which partitions a mesh based on the premise that a 3D object consists of a core body and its constituent protrusible pa...
Alexander Agathos, Ioannis Pratikakis, Stavros J. ...