A Single-Frame and Multi-Frame Cascaded Image Super-Resolution Method

被引:0
|
作者
Sun, Jing [1 ]
Yuan, Qiangqiang [2 ]
Shen, Huanfeng [1 ]
Li, Jie [2 ]
Zhang, Liangpei [3 ]
机构
[1] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Peoples R China
[2] Wuhan Univ, Sch Geodesy & Geomat, Wuhan 430079, Peoples R China
[3] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & Re, Wuhan 430079, Peoples R China
基金
中国国家自然科学基金;
关键词
super-resolution; deep learning; cascade model; resolution enhancement; regularized framework;
D O I
10.3390/s24175566
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The objective of image super-resolution is to reconstruct a high-resolution (HR) image with the prior knowledge from one or several low-resolution (LR) images. However, in the real world, due to the limited complementary information, the performance of both single-frame and multi-frame super-resolution reconstruction degrades rapidly as the magnification increases. In this paper, we propose a novel two-step image super resolution method concatenating multi-frame super-resolution (MFSR) with single-frame super-resolution (SFSR), to progressively upsample images to the desired resolution. The proposed method consisting of an L0-norm constrained reconstruction scheme and an enhanced residual back-projection network, integrating the flexibility of the variational model-based method and the feature learning capacity of the deep learning-based method. To verify the effectiveness of the proposed algorithm, extensive experiments with both simulated and real world sequences were implemented. The experimental results show that the proposed method yields superior performance in both objective and perceptual quality measurements. The average PSNRs of the cascade model in set5 and set14 are 33.413 dB and 29.658 dB respectively, which are 0.76 dB and 0.621 dB more than the baseline method. In addition, the experiment indicates that this cascade model can be robustly applied to different SFSR and MFSR methods.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] A multi-frame image super-resolution method
    Li, Xuelong
    Hu, Yanting
    Gao, Xinbo
    Tao, Dacheng
    Ning, Beijia
    [J]. SIGNAL PROCESSING, 2010, 90 (02) : 405 - 414
  • [2] Single image super-resolution under multi-frame method
    Shujin Zhu
    Yuehua Li
    [J]. Signal, Image and Video Processing, 2019, 13 : 331 - 339
  • [3] Single image super-resolution under multi-frame method
    Zhu, Shujin
    Li, Yuehua
    [J]. SIGNAL IMAGE AND VIDEO PROCESSING, 2019, 13 (02) : 331 - 339
  • [4] Combined Single and Multi-frame Image Super-resolution
    Gonbadani, Mohammad Mandi Afrasiabi
    Abbasfar, Aliazam
    [J]. 2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 237 - 242
  • [5] Neighborhood issue in single-frame image super-resolution
    Su, K
    Tian, Q
    Xue, Q
    Sebe, N
    Ma, JS
    [J]. 2005 IEEE International Conference on Multimedia and Expo (ICME), Vols 1 and 2, 2005, : 1123 - 1126
  • [6] Online multi-frame super-resolution of image sequences
    Xu, Jieping
    Liang, Yonghui
    Liu, Jin
    Huang, Zongfu
    Liu, Xuewen
    [J]. EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2018,
  • [7] Online multi-frame super-resolution of image sequences
    Jieping Xu
    Yonghui Liang
    Jin Liu
    Zongfu Huang
    Xuewen Liu
    [J]. EURASIP Journal on Image and Video Processing, 2018
  • [8] Handheld Multi-Frame Super-Resolution
    Wronski, Bartlomiej
    Garcia-Dorado, Ignacio
    Ernst, Manfred
    Kelly, Damien
    Krainin, Michael
    Liang, Chia-Kai
    Levoy, Marc
    Milanfar, Peyman
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2019, 38 (04):
  • [9] Multi-Frame Super-Resolution: A Survey
    Khattab, Mahmoud M.
    Zeki, Akram M.
    Alwan, Ali A.
    Badawy, Ahmed S.
    Thota, Lalitha Saroja
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND COMPUTING RESEARCH (IEEE ICCIC 2018), 2018, : 348 - 355
  • [10] Single-frame image super-resolution inspired by perceptual criteria
    Zhou, Fei
    Liao, Qingmin
    [J]. IET IMAGE PROCESSING, 2015, 9 (01) : 1 - 11