Volumetric representation for sparse multi-views

被引：1

作者：

Anantrasirichai, N. ^{[1
]}

Canagarajah, C. Nishan ^{[1
]}

Redmill, David W. ^{[1
]}

Bull, David R. ^{[1
]}

机构：

[1] Univ Bristol, Dept Elect & Elect Engn, Bristol BS8 1UB, Avon, England

来源：

2006 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP 2006, PROCEEDINGS | 2006年

关键词：

three-dimensional vision; image synthesis;

D O I：

10.1109/ICIP.2006.312545

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a novel volumetric representation for a sparse set of calibrated multi-view images of a non-Lambertian scene. The depth map of each reference view is registered into a volume and a simple algorithm to shape the volume is introduced. Particular colours are defined for each voxel to render a smooth and realistic image. Synthesized results demonstrate the good performance with the proposed scheme, both for parallel-camera and non-parallel-camera geometries.

引用

页码：1221 / +

页数：2

共 10 条

[1]

[Anonymous], P EUR C COMP VIS

[2]

BOYER E, 1996, P EUR C COMP VIS, P109

[3] Automatic reconstruction of stationary 3-D objects from multiple uncalibrated camera views [J].

Eisert, P ;

Steinbach, E ;

Girod, B .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2000, 10 (02) :261-277

[4]

ERNST F, 2001, P VIS MOD VIS STUTTG, P203

[5]

FELTS B, 2000, IEEE P ICIP 00, V1, P1004

[6]

Gargallo P, 2005, PROC CVPR IEEE, P885

[7]

Koch R., 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), P500, DOI 10.1109/ICIP.1999.822946

[8]

KOCH R, 1999, P DAGM 99, P413

[9]

RODLER FF, 1999, IEEE P 7 PAC C COMP, P108

[10]

Zhang JH, 2004, IEEE DATA COMPR CONF, P508

← 1 →