This paper addresses the problem of recognizing freeform 3D objects in point clouds. Compared to traditional approaches based on point descriptors, which depend on local informati...
Bertram Drost, Markus Ulrich, Nassir Navab, Slobod...
Linear perspective projection has served as the dominant imaging model in computer vision. Recent developments in image sensing make the perspective model highly restrictive. This...
Abstract. We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it...
In this paper, a function-based extension of Extensible 3D (X3D) is proposed. The extension allows authors to use analytical functions to define geometry, color, 3D texture as wel...
The bounding box representation employed by many popular object detection models [3, 6] implicitly assumes all pixels inside the box belong to the object. This assumption makes th...