Title
Adaptive depth map assisted matting in 3D video
Abstract
Depth map is widely adopted and available in the 3D research area. Combining the depth map with the matting techniques is helpful to the original matte and depth image based rendering in 3D. Herein, in this paper, a novel adaptive depth map assisted matting approach with concise integration is presented and applied to achieve favorable matting results. In this approach, the Lagrange-multiplier-free closed form solution is firstly derived to reduce the computation complexity and to increase matting accuracy. Based on the work of Levin et al. on closed form matting, an improved alpha matte is then achieved by introducing an adaptive smoothness criterion which is the function of depth map variance. Finally, the matting system is capable of working in a full automatical way by generating the trimap from the depth information. Simulation results demonstrate that the proposed method is able to efficiently generate an alpha matte with an roughly user specified scribbles or an automatically generated trimap.
Year
DOI
Venue
2011
10.1109/ICME.2011.6012043
ICME
Keywords
Field
DocType
automatic,matting accuracy,depth map,video signal processing,favorable matting result,lagrange-multiplier-free closed form solution,depth map variance,computational complexity reduction,smoothing methods,alpha matte,depth image based rendering,rendering (computer graphics),trimap generation,computational complexity,3d video,closed form matting,matting approach,matting technique,depth map variance function,depth information,adaptive depth,depth,adaptive depth map assisted matting technique,closed form,adaptive smoothness criterion,depth image,matting,smooth criterion,matting system,color,cost function,accuracy,lagrange multiplier,closed form solution,pediatrics
Computer vision,Computer graphics (images),Computer science,Closed-form expression,Artificial intelligence,Depth map,Image-based modeling and rendering,Smoothness,Computation complexity,Computational complexity theory
Conference
ISSN
ISBN
Citations 
1945-7871 E-ISBN : 978-1-61284-349-0
978-1-61284-349-0
3
PageRank 
References 
Authors
0.37
8
4
Name
Order
Citations
PageRank
Wenxiu Sun116020.79
Oscar C. Au21592176.54
Lingfeng Xu3539.81
Zhiding Yu442130.08