Abstract--This paper addresses the problem of efficient representation of scenes captured by distributed omnidirectional vision sensors. We propose a novel geometric model to descr...
The paper presents a novel coding technique based on approximate geometry for images taken from arbitrary recording positions around a 3-D scene. Such data structures occur in ima...
This paper presents a distributed and occlusion-robust coding scheme for multi-view omnidirectional images, which relies on the geometry of the 3D scene. The Wyner-Ziv coder uses ...
Stochastic transparency provides a unified approach to orderindependent transparency, anti-aliasing, and deep shadow maps. It augments screen-door transparency using a random sub...
Eric Enderton, Erik Sintorn, Peter Shirley, David ...
Geometry compression for VRML has been an important item on the wish-list of the Web3D Consortium since 1996. It was widely understood that a binary format would be required to al...