Title
Error compensation and reliability based view synthesis
Abstract
View synthesis offers a great flexibility in generating free viewpoint television (FTV) and 3D video (3DV). However, the depth-image-based view synthesis approach is very sensitive to errors in the camera parameters or poorly estimated depth maps (also called depth images). Because of these errors, three kinds of artifacts (blurring, contour, hole) are possibly introduced during the general synthesis process. Comparing to conventional methods which implement the view synthesis only in ideal case, in this paper, we propose to de sign an error compensation and reliability based view synthesis system where the potential errors are considered. The main contributions are highlighted as follows: Firstly, the camera parameter errors are compensated by a global homography transformation matrix. Secondly, the depth maps are classified into both reliable and unreliable regions and the reliability based weighting masks are built to blend synthesized images from two different views together. Finally, a reliability depth map based hole-filling technique is used to fill the existing holes. The experimental results demonstrate that these artifacts are efficiently reduced in the synthesized images.
Year
DOI
Venue
2011
10.1109/ICASSP.2011.5946662
ICASSP
Keywords
Field
DocType
video signal processing,view synthesis,three-dimensional television,matrix algebra,hole-filling technique,video cameras,reliability based,3d video,camera parameter errors,signal synthesis,artifacts reduction,error compensation,depth-image-based view synthesis approach,reliability,depth map error,homography transformation matrix,camera parameter error,free viewpoint television,reliability based view synthesis system,reliability based weighting masks,depth map estimation,visualization,depth map,color,three dimensional,pixel
Computer vision,Weighting,Visualization,Computer science,View synthesis,Homography,Pixel,Artificial intelligence,Depth map,Transformation matrix,Free viewpoint television
Conference
ISSN
ISBN
Citations 
1520-6149 E-ISBN : 978-1-4577-0537-3
978-1-4577-0537-3
4
PageRank 
References 
Authors
0.48
4
6
Name
Order
Citations
PageRank
Wenxiu Sun116020.79
Oscar C. Au21592176.54
Lingfeng Xu3539.81
Sung Him Chui4182.34
Chun Wing Kwok5111.53
Yujun Li610418.20