Premium
61.3: Stereoscopic 3D Content Depth Tuning Guided by Human Visual Models
Author(s) -
Yuan Chang,
Pan Hao,
Daly Scott
Publication year - 2011
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1889/1.3621486
Subject(s) - stereoscopy , computer science , depth perception , artificial intelligence , computer vision , matching (statistics) , image (mathematics) , block (permutation group theory) , perception , scaling , stereopsis , content (measure theory) , mathematics , psychology , statistics , mathematical analysis , neuroscience , geometry
Abstract We present a new approach for tuning stereoscopic 3D content based on viewers' comfort and preferences. 2D image disparities are computed by a block matching based estimation algorithm. Human visual comfort models are applied to analyze the image disparities and guide the depth tuning (shifting/scaling) algorithms in order to generate new stereo views with desired and comfortable depth perception. Real‐life image results are shown to demonstrate the effectiveness of our approach.