Paper Info
Title
An interactive system of stereoscopic video conversion
Abstract
With the recent booming of 3DTV industry, more and more stereoscopic videos are demanded by the market. This paper presents a system of converting conventional monocular videos to stereoscopic ones. In this system, an input video is firstly segmented into shots to reduce operations on similar frames. Then, automatic depth estimation and interactive image segmentation are integrated to obtain depth maps and foreground/background segments on selected key frames. Within each video shot, such results are propagated from key frames to non-key frames. Combined with a depth-to-disparity conversion method, the system synthesizes the counterpart (either left or right) view for stereoscopic display by warping the original frame according to disparity maps. For evaluation, we use human labeled depth map as the reference and compute both the mean opinion score (MOS) and Peak signal-to-noise ratio (PSNR) to valuate the converted video quality. Experiment results demonstrate that the proposed conversion system and methods achieves encouraging performance.
Year
DOI
Venue
2012
10.1145/2393347.2393374
ACM Multimedia 2001
Keywords
Field
DocType
depth-to-disparity conversion method,automatic depth estimation,stereoscopic video,stereoscopic video conversion,depth map,input video,interactive system,conventional monocular video,converted video quality,proposed conversion system,stereoscopic display,video shot,2d to 3d conversion
Computer graphics (images),Computer science,2D to 3D conversion,Image segmentation,Artificial intelligence,Depth map,Monocular,Video quality,Computer vision,Image warping,Stereoscopy,Mean opinion score,Multimedia
Conference
Citations 
PageRank 
References 
4
0.41
19
Authors
5
Name
Order
Citations
PageRank
Zhebin Zhang1434.08
Chen Zhou2222.44
Bo Xin3415.13
Yizhou Wang4116286.04
Wen Gao511374741.77