Presentation 2016-05-19
FPGA Implementation of a Super-Resolution System
Taito Manabe, Yuichiro Shibata, Kiyoshi Oguri,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we implement a real-time super-resolution system for moving images using a convolutional neural network on an FPGA, and evaluate its performance. Instead of pre-enlargement proposed in related works, we apply horizontal and/or vertical flips to network input images. This method prevents them from losing information, which enables super-resolution whose quality is superior to the system using pre-enlargement, even though the network scale and the size of filters are limited due to resource restriction of the FPGA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Super Resolution / Moving Images / Real-time / FPGA / Convolutional Neural Network / Deep Learning
Paper # RECONF2016-5
Date of Issue 2016-05-12 (RECONF)

Conference Information
Committee RECONF
Conference Date 2016/5/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English) FUJITSU LAB.
Topics (in Japanese) (See Japanese page)
Topics (in English) Reconfigurable Systems, etc.
Chair Minoru Watanabe(Shizuoka Univ.)
Vice Chair Masato Motomura(Hokkaido Univ.) / Yuichiro Shibata(Nagasaki Univ.)
Secretary Masato Motomura(Toshiba) / Yuichiro Shibata(Univ. of Tsukuba)
Assistant Kazuya Tanikagawa(Hiroshima City Univ.) / Takefumi Miyoshi(e-trees.Japan)

Paper Information
Registration To Technical Committee on Reconfigurable Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) FPGA Implementation of a Super-Resolution System
Sub Title (in English)
Keyword(1) Super Resolution
Keyword(2) Moving Images
Keyword(3) Real-time
Keyword(4) FPGA
Keyword(5) Convolutional Neural Network
Keyword(6) Deep Learning
1st Author's Name Taito Manabe
1st Author's Affiliation Nagasaki University(Nagasaki Univ.)
2nd Author's Name Yuichiro Shibata
2nd Author's Affiliation Nagasaki University(Nagasaki Univ.)
3rd Author's Name Kiyoshi Oguri
3rd Author's Affiliation Nagasaki University(Nagasaki Univ.)
Date 2016-05-19
Paper # RECONF2016-5
Volume (vol) vol.116
Number (no) RECONF-53
Page pp.pp.17-22(RECONF),
#Pages 6
Date of Issue 2016-05-12 (RECONF)