Premium
54.2: Natural Stereo Depth Creation Methodology for a Real‐time 2D‐to‐3D Image Conversion
Author(s) -
Iinuma T.,
Murata H.,
Yamashita S.,
Oyamada K.
Publication year - 2000
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 - 10.1889/1.1832883
Subject(s) - parallax , computer vision , artificial intelligence , computer science , stereo image , stereo display , depth perception , computer graphics (images) , 2d to 3d conversion , binocular disparity , contrast (vision) , image (mathematics) , stereo imaging , depth map , stereopsis , perception , neuroscience , biology
We propose a “Depth Creation by stereo Perception (DCP)” method that creates more natural and impressive 3D images than ever from input 2D images by their stereo perceptual information, which includes horizontal motion, color, contrast, sharpness, and composition. We also propose a “Linear Depth Control (LDC)” method that controls the binocular parallax of the created 3D images by their image depth position in order to improve the 3D effect of the converted images. And the real‐time 2D‐to‐3D image conversion unit implemented these new methods realizes more natural 3D images corresponding to various 3D displays from 2D images of any types and scenes.