Paper Info
Title
A Synthesis-Quality-Oriented Depth Refinement Scheme for MPEG Free Viewpoint Television (FTV)
Abstract
This paper addresses the problem of refining depth information from the received reference and depth images within the MPEG FTV framework. An analytical model is first developed to approximate the per-pixel synthesis distortion (caused by depth-image compression) as a function of depth-error variances, intensity variations, ground-truth depth and virtual camera locations. We then follow the model to detect unreliable depth pixels by inspecting intensity gradients and to refine their values with a candidate-based block disparity search. Additional side information is transmitted to make both operations robust against compression effects. Experimental results show that our scheme offers an average PSNR improvement of 1.2 dB over MPEG FTV and consistently outperforms the state-of-the-art methods. Moreover, it can remove synthesis artifacts to a great extent, producing a result that is very close in appearance to the ground-truth view image.
Year
DOI
Venue
2009
10.1109/ISM.2009.68
ISM
Keywords
Field
DocType
analytical model,depth-image compression,unreliable depth pixel,mpeg free viewpoint television,compression effect,mpeg ftv,ground-truth depth,mpeg ftv framework,additional side information,refining depth information,depth image,synthesis-quality-oriented depth refinement scheme,ground truth,transform coding,image compression,data compression,pixel,sensitivity
Computer vision,Virtual camera,Computer science,Transform coding,Side information,Image coding,Pixel,Artificial intelligence,Data compression,Distortion,Free viewpoint television
Conference
Citations 
PageRank 
References 
2
0.46
4
Authors
4
Name
Order
Citations
PageRank
Chun-Chi Chen119925.04
Yi-Wen Chen220.46
Fu-Yao Yang320.46
Wen-Hsiao Peng420933.15