Reconstructing dense light field from array of multifocus images for novel view synthesis

被引:32
作者
Kubota, Akira [1 ]
Aizawa, Kiyoharu
Chen, Tsuhan
机构
[1] Tokyo Inst Technol, Dept Informat Proc, Yokohama, Kanagawa 2268502, Japan
[2] Univ Tokyo, Dept Elect & Elect Engn, Tokyo 1138656, Japan
[3] Carnegie Mellon Univ, Dept Elect & Comp Engn, Pittsburgh, PA 15213 USA
关键词
blur; image-based rendering (IBR); light-field rendering (LFR); spatial invariant filter; view interpolation;
D O I
10.1109/TIP.2006.884938
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents a novel method for synthesizing a novel view from two sets of differently focused images taken by an aperture camera array for a scene consisting of two approximately constant depths. The proposed method consists of two steps. The first step is a view interpolation to reconstruct an all-in-focus dense light field of the scene. The second step is to synthesize a novel view by a light-field rendering technique from the reconstructed dense light field. The view interpolation in the first step can be achieved simply by linear filters that are designed to shift different object regions separately, without region segmentation. The proposed method can effectively create a dense array of pin-hole cameras (i.e., all-in-focus images), so that the novel view can be synthesized with better quality.
引用
收藏
页码:269 / 279
页数:11
相关论文
共 29 条
[1]  
Adelson E.H., 1991, Computational Models of Visual Processing, V1, P3
[2]   Producing object-based special effects by fusing multiple differently focused images [J].
Aizawa, K ;
Kodama, K ;
Kubota, A .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2000, 10 (02) :323-330
[3]   Sea of images - A dense sampling approach for rendering large indoor environments [J].
Aliaga, DG ;
Funkhouser, T ;
Yanovsky, D ;
Carlbom, I .
IEEE COMPUTER GRAPHICS AND APPLICATIONS, 2003, 23 (06) :22-30
[4]   Seeing behind the scene: Analysis of photometric properties of occluding edges by the reversed projection blurring model [J].
Asada, N ;
Fujiwara, H ;
Matsuyama, T .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (02) :155-167
[5]  
Chai JX, 2000, COMP GRAPH, P307, DOI 10.1145/344779.344932
[6]   A space-sweep approach to true multi-image matching [J].
Collins, RT .
1996 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1996, :358-363
[7]   STRUCTURE FROM STEREO - A REVIEW [J].
DHOND, UR ;
AGGARWAL, JK .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1989, 19 (06) :1489-1510
[8]  
Droese M., 2004, Proceedings of 11th International Workshop on Systems, Signals and Image Processing. Ambient Multimedia, P247
[9]   AN INVESTIGATION OF METHODS FOR DETERMINING DEPTH FROM FOCUS [J].
ENS, J ;
LAWRENCE, P .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1993, 15 (02) :97-108
[10]  
Geys I, 2004, 2ND INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, P534