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
  • [41] Example Based Single-frame Image Super-resolution by Support Vector Regression
    Li, Dalong
    Simske, Steven
    [J]. JOURNAL OF PATTERN RECOGNITION RESEARCH, 2010, 5 (01): : 104 - 118
  • [42] Handling Motion Blur in Multi-Frame Super-Resolution
    Ma, Ziyang
    Liao, Ken
    Tao, Xin
    Xu, Li
    Jia, Jiaya
    Wu, Enhua
    [J]. 2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 5224 - 5232
  • [43] Single-Frame Image Super-Resolution based on Singular Square Matrix Operator
    Rashkevych, Yurii
    Peleshko, Dmytro
    Vynokurova, Olena
    Izonin, Ivan
    Lotoshynska, Natalia
    [J]. 2017 IEEE FIRST UKRAINE CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (UKRCON), 2017, : 944 - 948
  • [44] A nonconvex fractional order variational model for multi-frame image super-resolution
    Laghrib, A.
    Ben-Loghfyry, A.
    Hadri, A.
    Hakim, A.
    [J]. SIGNAL PROCESSING-IMAGE COMMUNICATION, 2018, 67 : 1 - 11
  • [45] Preserving quality in minimum frame selection within multi-frame super-resolution
    Rahimi, Akbar
    Moallem, Payman
    Shahtalebi, Kamal
    Momeni, Mehdi
    [J]. DIGITAL SIGNAL PROCESSING, 2018, 72 : 19 - 43
  • [46] Novel image restoration method based on multi-frame super-resolution for atmospherically distorted images
    Li, Yinhao
    Ogawa, Katsuhisa
    Iwamoto, Yutaro
    Chen, Yen-Wei
    [J]. IET IMAGE PROCESSING, 2020, 14 (01) : 168 - 175
  • [47] Depth image super-resolution via multi-frame registration and deep learning
    Tseng, Ching Wei
    Su, Hong-Ren
    Lai, Shang-Hong
    Liu, JenChi
    [J]. 2016 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2016,
  • [48] Multi-frame super-resolution for long range captured iris polar image
    Deshpande, Anand
    Patavardhan, Prashant
    [J]. IET BIOMETRICS, 2017, 6 (02) : 108 - 116
  • [49] A Gesture Recognition Framework Based on Multi-frame Super-resolution Image Sequence
    Li, Yuanhao
    Dong, Gangqi
    Huang, Panfeng
    Ma, Zhiqiang
    Wang, Xiang
    [J]. 2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 4519 - 4524
  • [50] Application of multi-frame approach in single-frame blind deconvolution
    Shi, Dongfeng
    Fan, Chengyu
    Shen, Hong
    Zhang, Pengfei
    Zhang, Jinghui
    Qiao, Chunhong
    Wang, Yingjian
    [J]. OPTICS COMMUNICATIONS, 2012, 285 (24) : 4937 - 4940