28 February 2012 Stereoscopic image-inpainting-based view synthesis algorithm for glasses-based and glasses-free 3D displays
Author Affiliations +
Abstract
We propose a new algorithm for synthesis of novel views based on existing stereo 3D imagery for both glasses-based and glasses-free 3D displays. Due to the often differing audience preferences for stereo depth perception on glasses-based displays, the range of perceived 3D depth needs to be either compressed or expanded. The proposal algorithm enables this depth adjustment through the synthesis of new virtual views, by incorporating intensity, disparity, and geometric saliency cues present in the stereo image pair. The proposed algorithm is further capable of eliminating the grid quantization artifacts, a common phenomenon when manipulating discrete image disparities. The algorithm can be also applied for generating multiple views for glasses-free 3D displays, based on the same stereo imagery. Successful results are demonstrated on real-world video datasets, and evaluated and validated by human subject studies.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chang Yuan, Chang Yuan, Chris Liao, Chris Liao, Hao Pan, Hao Pan, } "Stereoscopic image-inpainting-based view synthesis algorithm for glasses-based and glasses-free 3D displays", Proc. SPIE 8288, Stereoscopic Displays and Applications XXIII, 82882J (28 February 2012); doi: 10.1117/12.909828; https://doi.org/10.1117/12.909828
PROCEEDINGS
13 PAGES


SHARE
Back to Top