Generation of layered depth images from multi-view video

被引：0

作者：

Cheng, Xiaoyu ^{[1
]}

Sun, Lifeng ^{[1
]}

Yang, Shiqiang ^{[1
]}

机构：

[1] Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China

来源：

2007 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-7 | 2007年

关键词：

layered depth image (LDI); multi-view video; three-dimensional image;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The feature of rendering arbitrary view make layered depth image (LDI) be suitable to present multi-view video data and provide interactivity form such as free view video(FVV). However, visual artifacts occured in the rendered result limit the practicality of LDI. In this paper, we proposed an approach to deal with this problem during generating of LDI, which refines colors of the depth pixels by choosing proper candidate depth pixels, removes matting effects by projecting LDI backward to reference views, and eliminate the gaps or holes dure to disocclusion and undersample by local background interpolation. Expermental results show that our approach is practicable and efficient.

引用

页码：2477 / 2480

页数：4

共 10 条

[1]

[Anonymous], P SIGGRAPH 2002

[2]

[Anonymous], P SIGGRAPH

[3]

Chang CF, 1999, COMP GRAPH, P291, DOI 10.1145/311535.311571

[4]

Fitzgibbon A, 2003, NINTH IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, VOLS I AND II, PROCEEDINGS, P1176

[5]

HASINOFF SW, 2004, P 2004 IEEE C COMP V, P170

[6]

MCMILLAN L, 1995, 95005 U N CAR CHAP H

[7]

Schirmacher H, 2000, PROC GRAPH INTERF, P87

[8] Photorealistic scene reconstruction by voxel coloring [J].

Seitz, SM ;

Dyer, CR .

1997 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1997, :1067-1073

[9]

Shade J., 1998, Computer Graphics. Proceedings. SIGGRAPH 98 Conference Proceedings, P231, DOI 10.1145/280814.280882

[10]

Wexler Y, 2002, LECT NOTES COMPUT SC, V2352, P487

← 1 →