Robust Computer Vision Techniques for High-quality 3-D Modeling（セミナー・シンポジウム）
29 Sept 15:00-16:30
Collaboration 7
Title: Robust Computer Vision Techniques for High-quality 3-D Modeling
Abstract
For the 3D reconstruction of static and dynamic scenes, we have developed several robust computer
vision methods ranging from the image enhancement algorithms to the novel sensor-fusion systems.
In this talk, we first present a rank based approach to recover the camera response function, which is
crucial for many color image processing problems such as high dynamic range imaging and photo-
consistent mosaicking. We also present an optimization framework to compute an optimal binary
sequence for the coded exposure imaging. The proposed binary sequence has shown better deblurring
and resolution enhancement results compared to the one computed by the previous random search
method. To improve the quality of the input image, we also extend the robust PCA by introducing a
new framework which takes into account the rank constraint explicitly. Our approach outperforms the
conventional robust PCA in achieving the image enhancement while removing any outliers. The second
part of the talk introduces a new sensor fusion system to capture the high-quality 3D information
accurately and efficiently. The fusion system combines the geometric information computed by cameras
with the photometric information. This new approach allows boosting the advantages of the two
approaches and complements the weakness of the two. Specifically, the rough geometric data obtained
by a depth sensor is used as an initial estimate to obtain the high-quality 3-D shape by a shape-from-
shading approach. In addition, an intelligent vehicle, the KAIST-Eurecar, will be introduced.
Bio:
Professor Kweon received the B.S. and the M.S. degrees in Mechanical Design and Production
Engineering from Seoul National University, Korea, in 1981 and 1983, respectively, and the Ph.D.
degree in Robotics from the Robotics Institute at Carnegie Mellon University in 1990. He worked for
Toshiba R&D Center, Japan, and joined KAIST in 1992. He is a professor of electrical engineering
(EE) and the director for the National Core Research Center ? P3 DigiCar Center at KAIST. He served
as the department head of Automation and Design Engineering (ADE) at KAIST in 1995-1998.
Professor Kweon's research interests include computer vision and robotics. He has co-authored several
books, including "Metric Invariants for Camera Calibration," and more than 400 technical papers. He
served as a Founding Associate-Editor-in-Chief for gInternational Journal of Computer Vision and
Applicationsh, and has been an Editorial Board Member for gInternational Journal of Computer Visionh
since 2005.
Professor Kweon is a member of many computer vision and robotics conference program committees
and has been a program co-chair for several conferences and workshops. He was a general co-chair of
the 2012 Asian Conference on Computer Vision (ACCV) Conference.
Professor Kweon received many awards from the international and domestic conferences, including
"The IEEE Transaction on CSVT Best Paper Award 2014" and "The Best Student Paper Runner-up
Award in the IEEE-CVPR' 2009". Professor Kweon has also earned several honors at KAIST, including
the 2002 Best Teaching Award in EE. In 2001, he received the KAIST Research Award. He is a
member of KROS and IEEE.
