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 · 2018
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 superresolution via patch-based deep neural network (SR-PDNN) rather than a convolutional neural network (CNN).Despite the very simple end-toend 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).