User-perspective augmented reality magic lens from gradients

Autor:	Tobias Höllerer, Domagoj Baricevic, Matthew Turk, Pradeep Sen
Rok vydání:	2014
Předmět:	Computer science business.industry Computer graphics (images) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Magic lens Stereo matching Computer vision Augmented reality Artificial intelligence Image-based modeling and rendering business Rendering (computer graphics)
Zdroj:	VRST
DOI:	10.1145/2671015.2671027
Popis:	In this paper we present a new approach to creating a geometrically-correct user-perspective magic lens and a prototype device implementing the approach. Our prototype uses just standard color cameras, with no active depth sensing. We achieve this by pairing a recent gradient domain image-based rendering method with a novel semi-dense stereo matching algorithm inspired by PatchMatch. Our stereo algorithm is simple but fast and accurate within its search area. The resulting system is a real-time magic lens that displays the correct user perspective with a high-quality rendering, despite the lack of a dense disparity map.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::25a3e356b23502a961bd2dfe414fa5c4 https://doi.org/10.1145/2671015.2671027 Zobrazit plný text záznamu