A Real-Time Learning-Based Super-Resolution System Using Direct Simple Functions

被引：0
|
作者：
Zha, Daolu [1 ]
Jin, Xi [1 ]
Shang, Rui [2 ]
Yang, Pengfei [1 ]
机构：
[1] Univ Sci & Technol China, Sch Phys Sci, Hefei, Anhui, Peoples R China
[2] Suzhou Graphichina Microelect Technol Co Ltd, Suzhou, Peoples R China
来源：
2018 IEEE 29TH INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS (ASAP) | 2018年
关键词：
Super-Resolution; Real-Time; FPGA;
D O I：
暂无
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper proposes a real-time super-resolution (SR) system. The proposed system performs a fast SR algorithm that generates a high-resolution image from a low-resolution image using direct regression functions. The system implemented on a Xilinx Virtex 7 field programmable gate array achieves output resolution of 3840 x 2160 (UHD) at 200 fps and 2000Mpixels/s throughput. Experimental results show that the proposed system provides high image quality for real-time applications.
引用
收藏
页码：77 / 80
页数：4
相关论文
共 50 条
  • [1] A Real-Time Learning-Based Super-Resolution System on FPGA
    Zha, Daolu
    Jin, Xi
    Shang, Rui
    Yang, Pengfei
    PARALLEL PROCESSING LETTERS, 2020, 30 (04)
  • [2] A Real-Time FHD Learning-Based Super-Resolution System Without a Frame Buffer
    Yang, Ming-Che
    Liu, Kuan-Ling
    Chien, Shao-Yi
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2017, 64 (12) : 1407 - 1411
  • [3] Realizing real-time deep learning-based super-resolution applications on Integrated GPUs
    Kim, SungYe
    Bindu, Preeti
    2016 15TH IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS (ICMLA 2016), 2016, : 693 - 696
  • [4] FPGA Implementation of a Real-Time Super-Resolution System Using Flips and an RNS-Based CNN
    Manabe, Taito
    Shibata, Yuichiro
    Oguri, Kiyoshi
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2018, E101A (12) : 2280 - 2289
  • [5] Limitations of Learning-Based Super-Resolution
    Shoji, Hiroki
    Gohshi, Seiichi
    2015 INTERNATIONAL SYMPOSIUM ON INTELLIGENT SIGNAL PROCESSING AND COMMUNICATION SYSTEMS (ISPACS), 2015, : 646 - 651
  • [6] Winograd-based Real-time Super-Resolution System on FPGA
    Shi, Bizhao
    Tang, Zhucheng
    Luo, Guojie
    Jiang, Ming
    2019 INTERNATIONAL CONFERENCE ON FIELD-PROGRAMMABLE TECHNOLOGY (ICFPT 2019), 2019, : 423 - 426
  • [7] A Real-Time Super-Resolution Method Based on Convolutional Neural Networks
    Shipeng Fu
    Lu Lu
    Hu Li
    Zhen Li
    Wei Wu
    Anand Paul
    Gwanggil Jeon
    Xiaomin Yang
    Circuits, Systems, and Signal Processing, 2020, 39 : 805 - 817
  • [8] An FPGA-based design for real-time super-resolution reconstruction
    Marin, Yoan
    Miteran, Johel
    Dubois, Julien
    Heyrman, Barthelemy
    Ginhac, Dominique
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2020, 17 (06) : 1769 - 1785
  • [9] A Real-Time Super-Resolution Method Based on Convolutional Neural Networks
    Fu, Shipeng
    Lu, Lu
    Li, Hu
    Li, Zhen
    Wu, Wei
    Paul, Anand
    Jeon, Gwanggil
    Yang, Xiaomin
    CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2020, 39 (02) : 805 - 817
  • [10] An FPGA-based design for real-time super-resolution reconstruction
    Yoan Marin
    Johel Miteran
    Julien Dubois
    Barthélémy Heyrman
    Dominique Ginhac
    Journal of Real-Time Image Processing, 2020, 17 : 1769 - 1785
12345