Large Motion Video Super-Resolution with Dual Subnet and Multi-Stage Communicated Upsampling

被引:0
|
作者
Liu, Hongying [1 ]
Zhao, Peng [1 ]
Ruan, Zhubo [1 ]
Shang, Fanhua [1 ,2 ]
Liu, Yuanyuan [1 ]
机构
[1] Xidian Univ, Sch Artificial Intelligence, Key Lab Intelligent Percept & Image Understanding, Minist Educ, Xian, Peoples R China
[2] Peng Cheng Lab, Shenzhen, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Video super-resolution (VSR) aims at restoring a video in low-resolution (LR) and improving it to higher-resolution (HR). Due to the characteristics of video tasks, it is very important that motion information among frames should be well concerned, summarized and utilized for guidance in a VSR algorithm. Especially, when a video contains large motion, conventional methods easily bring incoherent results or artifacts. In this paper, we propose a novel deep neural network with Dual Subnet and Multi-stage Communicated Upsampling (DSMC) for super-resolution of videos with large motion. We design a new module named U-shaped residual dense network with 3D convolution (U3D-RDN) for fine implicit motion estimation and motion compensation (MEMC) as well as coarse spatial feature extraction. And we present a new Multi-Stage Communicated Upsampling (MSCU) module to make full use of the intermediate results of upsampling for guiding the VSR. Moreover, a novel dual subnet is devised to aid the training of our DSMC, whose dual loss helps to reduce the solution space as well as enhance the generalization ability. Our experimental results confirm that our method achieves superior performance on videos with large motion compared to state-of-the-art methods.
引用
收藏
页码:2127 / 2135
页数:9
相关论文
共 50 条
  • [41] Video Super-Resolution Based on Block Motion Estimation and Gradient Magnitude
    Anagun, Yildiray
    Seke, Erol
    Adar, Nihat
    2015 INTERNATIONAL SYMPOSIUM ON INNOVATIONS IN INTELLIGENT SYSTEMS AND APPLICATIONS (INISTA) PROCEEDINGS, 2015, : 77 - 82
  • [42] Edge-based Motion and Intensity Prediction for Video Super-Resolution
    Wang, Jen-Wen
    Chiu, Ching-Te
    2014 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2014, : 1039 - 1043
  • [43] Super-resolution video enhancement based on a constrained set of motion vectors
    Ivanovski, ZA
    Karam, LJ
    Abousleman, GP
    Visual Information Processing XIV, 2005, 5817 : 124 - 132
  • [44] Handling Motion Blur in Multi-Frame Super-Resolution
    Ma, Ziyang
    Liao, Ken
    Tao, Xin
    Xu, Li
    Jia, Jiaya
    Wu, Enhua
    2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2015, : 5224 - 5232
  • [45] Dual-Stream Fusion Network for Spatiotemporal Video Super-Resolution
    Tseng, Min-Yuan
    Chen, Yen-Chung
    Lee, Yi-Lun
    Lai, Wei-Sheng
    Tsai, Yi-Hsuan
    Chiu, Wei-Chen
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2683 - 2692
  • [46] Adapting Image Super-Resolution State-of-the-arts and Learning Multi-model Ensemble for Video Super-Resolution
    Li, Chao
    He, Dongliang
    Liu, Xiao
    Ding, Yukang
    Wen, Shilei
    2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2019), 2019, : 2033 - 2040
  • [47] MSRFSR: Multi-Stage Refining Face Super-Resolution With Iterative Collaboration Between Face Recovery and Landmark Estimation
    Hajian, Amir
    Aramvith, Supavadee
    IEEE ACCESS, 2024, 12 : 56951 - 56972
  • [48] Multi-stage remote sensing super-resolution network with deep fusion and structure enhancement based on CNN and transformer
    Jingyi Liu
    Xiaomin Yang
    Signal, Image and Video Processing, 2025, 19 (5)
  • [49] Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
    Li, Qiang
    Yuan, Yuan
    Jia, Xiuping
    Wang, Qi
    arXiv, 2022,
  • [50] Dual-Stage Approach Toward Hyperspectral Image Super-Resolution
    Li, Qiang
    Yuan, Yuan
    Jia, Xiuping
    Wang, Qi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 31 (7252-7263) : 7252 - 7263