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

Reo AOKI  Kousuke IMAMURA  Akihiro HIRANO  Yoshio MATSUDA  

IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.11   pp.2808-2817
Publication Date: 2018/11/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDP7081
Type of Manuscript: PAPER
Category: Image Processing and Video Processing
super-resolution,  deep neural network,  deep leaning,  real-time processing,  

Full Text: PDF(1.4MB)
>>Buy this Article

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).