Paper Info
Title
3D space representation using epipolar plane depth image
Abstract
We propose a novel 3D space representation for multi-view video, using epipolar plane depth images (EPDI). Multi-view video plus depth (MVD) is used as common data format for FTV(Free-viewpoint TV), which enables synthesizing virtual view images. Due to large amount of data and complexity of the multi-view video coding (MVC), compression of MVD is a challenging issue. We address this problem and propose a new representation that is constructed from MVD using rayspace. MVD is converted into image and depth ray-spaces. The proposed representation is obtained by converting each of ray-spaces into a global depth map and a texture map using EPDI. Experiments demonstrate the analysis of this representation, and its efficiency.
Year
DOI
Venue
2010
10.1109/PCS.2010.5702472
Picture Coding Symposium
Keywords
Field
DocType
image processing,video coding,3D space representation,data format,epipolar plane depth image,free-viewpoint TV,global depth map,multi-view video coding,multi-view video plus depth,ray-space,texture map,EPDI,EPI,FTV,GDM,Ray-Space,Texture Map
Iterative reconstruction,Computer vision,Texture mapping,Common Data Format,Epipolar geometry,Computer science,Image processing,Pixel,Artificial intelligence,Depth map,Encoding (memory)
Conference
ISBN
Citations 
PageRank 
978-1-4244-7134-8
2
0.40
References 
Authors
8
4
Name
Order
Citations
PageRank
Ishibashi, T.120.40
Yendo, T.2354.67
Tehrani, M.P.320.74
Toshiaki Fujii449863.04