The search functionality is under construction.
The search functionality is under construction.

High-Performance Super-Resolution via Patch-Based Deep Neural Network for Real-Time Implementation

Reo AOKI, Kousuke IMAMURA, Akihiro HIRANO, Yoshio MATSUDA

  • Full Text Views

    0

  • Cite this

Summary :

Recently, Super-resolution convolutional neural network (SRCNN) is widely known as a state of the art method for achieving single-image super resolution. However, performance problems such as jaggy and ringing artifacts exist in SRCNN. Moreover, in order to realize a real-time upconverting system for high-resolution video streams such as 4K/8K 60 fps, problems such as processing delay and implementation cost remain. In the present paper, we propose high-performance super-resolution via patch-based deep neural network (SR-PDNN) rather than a convolutional neural network (CNN). Despite the very simple end-to-end learning system, the SR-PDNN achieves higher performance than the conventional CNN-based approach. In addition, this system is suitable for ultra-low-delay video processing by hardware implementation using an application-specific integrated circuit (ASIC) or a field-programmable gate array (FPGA).

Publication
IEICE TRANSACTIONS on Information Vol.E101-D No.11 pp.2808-2817
Publication Date
2018/11/01
Publicized
2018/08/20
Online ISSN
1745-1361
DOI
10.1587/transinf.2018EDP7081
Type of Manuscript
PAPER
Category
Image Processing and Video Processing

Authors

Reo AOKI
  Kanazawa University,Visual Technologies (ASIC)
Kousuke IMAMURA
  Kanazawa University
Akihiro HIRANO
  Kanazawa University
Yoshio MATSUDA
  Kanazawa University

Keyword