Video Super-resolution by Generative Adversarial Network with 3D Convolutional Neural Networks

Kohei Moriyama, Naoki Ono, Kohei Inoue, Kenji Hara

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

抄録

For effective super-resolution processing of video images, video images should not be processed as frame-by-frame two-dimensional information, but as spatio-temporal information, including information in the time axis direction. Most of the proposed video super-resolution processing based on deep learning uses 2D convolutional neural networks (CNNs). Therefore, the system is based on the 2D CNNs with the additional processing related to change from frame to frame. Instead of processing video images separately in space and time, comprehensive processing as spatio-temporal information can be expected to be more flexible and effective. In this research, we propose a video super-resolution process that processes spatio-temporal information by 3D-CNNs and GAN (Generative adversarial networks). By using 3D-CNNs, the configuration does not require motion alignment as preprocessing. Since the essential purpose of the super-resolution process is to predict missing high-frequency components, we added a process that directly predicts the difference between the high-resolution image and the corresponding bicubic interpolated low-resolution image.

本文言語英語
ホスト出版物のタイトルInternational Workshop on Advanced Imaging Technology, IWAIT 2023
編集者Masayuki Nakajima, Jae-Gon Kim, Kwang-deok Seo, Toshihiko Yamasaki, Jing-Ming Guo, Phooi Yee Lau, Qian Kemao
出版社SPIE
ISBN(電子版)9781510663084
DOI
出版ステータス出版済み - 2023
イベント2023 International Workshop on Advanced Imaging Technology, IWAIT 2023 - Jeju, 韓国
継続期間: 1月 9 20231月 11 2023

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
12592
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

会議

会議2023 International Workshop on Advanced Imaging Technology, IWAIT 2023
国/地域韓国
CityJeju
Period1/9/231/11/23

!!!All Science Journal Classification (ASJC) codes

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「Video Super-resolution by Generative Adversarial Network with 3D Convolutional Neural Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル