Akira Kubota, Ph. D
AFFILIATIONS | RESEARCH_TOPICS | PUBLICATIONS
AFFILIATIONS
· Visiting scholar at Advanced Multimedia Processing Laboratory (AMP lab)
in department of Electrical and Computer Engineering in Carnegie Mellon
University (Oct. 2003 -)
Mailing Address:
Department of ECE, Carnegie Mellon
University,
5000 Forbes Ave., Pittsburgh, PA
15213-3890, USA
Office: Porter Hall B42, Phone: +1-412-268-7114, Fax: +1-412-268-1679
E-mail: kubota@hal.t.u-tokyo.ac.jp
· Research associate at University of Tokyo (Apr. 2002 -)
· Young scientist researcher of Japan Society for the Promotion of Science
(JSPS). (Apr. 2002 -)
RESEARCH TOPICS
n
All Focused Light Field
Rendering by Fusion
Abstract: We present a novel reconstruction method that can
synthesize an all in-focus view from under-sampled light fields, significantly
suppressing aliasing artifacts. The presented method consists of two steps; 1)
rendering multiple views at a given view point by performing light field
rendering with different focal plane depths; 2) iteratively reconstructing the
all in-focus view by fusing the multiple views. We model the multiple views and
the desired all in-focus view as a set of linear equations with a combination
of textures at the focal depths. Aliasing artifacts can be modeled as spatially
(shift) varying filters. We can solve this set of linear equations by using an
iterative reconstruction approach. This method effectively integrates focused
regions in each view into an all in-focus view without any local processing
steps such as estimation of depth or segmentation of the focused regions.
Keywords: Image-based rendering, Light field rendering,
Image fusion, Shift-variant filter
FOr more information: See
paper in Eurographics
Symposium on Rendering 2004
n
Reconstructing Dense Light Field
from a Multi-Focus Images Array
This figure: Sparse epipolar-plane
images (EPI) with different focus for two-depth scene in (a) and (b) are
combined into an all focused and dense EPI in (c).
Abstract: We present a novel method for synthesizing a new view
from two sets of differently focused images taken by a sparse camera array for
a scene of two approximately constant depths. The proposed method consists of
two steps. The first step is a view interpolation to reconstruct an all-focused
dense light field of the scene. The second step is to synthesize a novel view
by light-field rendering technique from the reconstructed dense light field.
The view interpolation can be achieved simply by linear filters that are
designed to convert the defocus effects to the parallax effects without
estimating the depth map of the scene. The proposed method can effectively
create a dense array of pin-hole cameras (i.e., all-focused images), so that
the final novel view is better than traditional method using sparse array of
cameras.
Keywords: Image-based rendering, Light field rendering, Linear filter,
blur, epipolar-plane image, interpolation
FOr more information: see
paper in Int. Conf. on Multimedia and Expo.
2004
Other
Research Topics (under construction)
n
All focus image generation using
linear filtering of differently focused images
n
Producing special visual effects
by fusing multiple focused images
n
Depth from focus; 3D modeling and
all focused image generation from microscopic images
PUBLICATIONS (selected)
n
Journal
Papers
K. Aizawa, K. Kodama, A. Kubota, “Producing
Object Based Special Effects by Fusing Multiple Differently Focused Images,”
IEEE Trans. Circuit and Systems for Video
Technology, Special Issue on 3D Video Technology, pp.323-330, March 2000
(There are 4 journal papers published in
Japan)
n
Book
Chapter
K. Aizawa, A. Kubota, K. Kodama, “Implicit 3D
approach to image generation: Object based visual effects by linear processing
of multiple differently focused images,” Multi-Image Search and Analysis, R. Klette, Th. Huang, G. Gimel'farb
(eds.), LNCS 2032, pp.226-237, Springer, 2001.
n
International
Conference
2004
A. Kubota, K. Aizawa, T.
Chen, “Virtual View Synthesis through Linear Processing without Geometry,” IEEE Int. Conf. Image Processing (ICIP2004), Oct. 24-27, 2004 (accepted) [PDF, 376KB]
K.
Takahashi, A. Kubota, T.
Naemura, “A Focus Measure for Light Field Rendering,” IEEE Int. Conf. Image Processing (ICIP2004), Oct. 24-27, 2004 (accepted) [PDF]
A. Kubota, K.
Takahashi, K. Aizawa, T. Chen, “All-Focused Light Field Rendering,” Eurographics
Symposium on Rendering (EGSR2004), June 21-23, 2004 [PDF,
2.8MB]
A. Kubota, K. Aizawa, T. Chen,
“Reconstructing Dense Light Field from a Multi-Focus Images Array,” IEEE
Conference on Multimedia and Expo 2004 (ICME2004), June 27-30, 2004 [PDF, 378KB]
2003
A. Kubota, K. Aizawa, “A novel image-based
rendering method by linear filtering of multiple focused images acquired by a
camera array,” IEEE Int. Conf. Image Processing (ICIP2003) Vol. III, pp.
701-704, Sep.13-17, 2003, Barcelona, Spain
K. Takahashi, A. Kubota, T. Naemura, “All in-focus image synthesis from under-sampled
light fields,” 13th Int. Conf. on Artificial Reality and Telexistence
(ICAT2003), pp. 249–256, Dec. 3-5, 2003, Tokyo, Japan [PDF]
2002
A. Kubota, K. Aizawa, “Arbitrary view and
focus image generation: Rendering object-based shifting and focusing effect by
linear filtering,” IEEE Int. Conf. Image Processing (ICIP2002) Vol. I, pp. 489-
492, MA-P.7.11, Sep.23-25, 2002, Rochester, NY [PDF, 2.4MB]
2001
A. Kubota, K. Aizawa, “A new approach to
depth range detection by producing depth-dependent blurring effect,” IEEE Int.
Conf. on Image Processing (ICIP2001), Vol.III,
pp.740-743, Oct. 7-10, 2001, Thessaloniki, Greece.
Y. Tsubaki, A.
Kubota, K. Aizawa, “All-focused
image generation and 3D modelling of microscopic images of insects,”
IEEE Int. Conf. on Image Processing (ICIP2001), Vol.II,
pp.197-200, Oct. 7-10, 2001, Thessaloniki, Greece
2000
A. Kubota, K. Aizawa, "Inverse filters
for reconstruction of arbitrarily focused images from two differently focused
images," IEEE Int. Conf. on Image Processing 2000 (ICIP'2000), Vol. I,
pp.101-104, Sep. 10-13 2000, Vancouver, Canada [PDF,
650kB]
1999
A. Kubota, K. Kodama, K. Aizawa,
"Registration and blur estimation methods for multiple differently focused
images,'' IEEE International Conference on Image Processing 99 (ICIP '99) Vol.
II, pp.447-451, Oct. 24-28 1999, Kobe, Japan
Last
update: July 8, 2004