[image 02433] 講演会(5/29)のご案内

[Akihiro Sugimoto]

皆様

下記の講演会を開催します。事前登録不要、参加費不要ですので、
ふるってご参加ください。

杉本

------------------------------------------------------------
日時:   5月29日(月曜日) 16:30 - 17:30 

場所:   国立情報学研究所 　1208号室(12F)
           (東京都千代田区一ツ橋）
            http://www.nii.ac.jp/about/access/

講演者:     Prof. Shang-Hong Lai
                National Tsing Hua University, Hsinchu, Taiwan 
                http://www.cs.nthu.edu.tw/~lai/

タイトル:  Image completion and restoration with deep learning

アブストラクト:
Recent advances in several image processing problems, such as 
image super-resolution, image completion and image restoration, 
have shown remarkable progress by using deep learning techniques. 
In this talk, I will present some of our recent research works on
different image processing problems with carefully designed deep
learning networks. For image completion with arbitrary shape of image
corruption, we propose a lightweight CNN model with conditional
generative adversarial networks (GANs) by using a stable adversarial
training scheme. For image restoration, we focus on reconstructing
fingerprint ridge structure from a corrupted fingerprint image. The
proposed CNN model consists of two streams that reconstruct the
?ngerprint image and orientation ?eld simultaneously. For depth image
super-resolution, we integrate several techniques, including multi-frame
fusion, guided filtering, and deep learning, to enhance the quality and
resolution of depth images. Finally, I will show some experimental
results to demonstrate the superior performance of the proposed 
methods compared to the existing methods.

Bio: 
Shang-Hong Lai received the Ph.D. degree in electrical and computer 
engineering from University of Florida, U.S.A., in 1995. Subsequently,
he joined Siemens Corporate Research in Princeton, New Jersey, as a
member of technical staff. Since 1999, he came back to Taiwan and became
a faculty member in the Department of Computer Science, National Tsing
Hua University, Taiwan. He is currently a professor and the department
chair in the same department. In 2004, he was a visiting scholar with
Princeton University. Dr. Lai’s research interests include computer
vision, image processing, machine learning, and multimedia signal
processing. He has authored more than 200 papers published in the
related international journals and conferences. Dr. Lai has served as an
area chair or a program committee member for a number of international
conferences, including CVPR, ICCV, ECCV, ACCV, ICPR, PSIVT, ACPR, ACM
Multimedia and ICME. He was a program co-chair for ACCV'16 and several
international workshops. Moreover, he has served as an associate editor
for Journal of Signal Processing Systems and IPSJ Transactions on
Computer Vision and Applications. He also served as a guest editor for
special issues in several international journals.

------------------