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
  • [21] Hyperspectral image super-resolution via a multi-stage scheme without employing spatial degradation
    Cao, Xuheng
    Lian, Yusheng
    Liu, Zilong
    Zhou, Han
    Bin, Wang
    Zhang, Wan
    Huang, Beiqing
    OPTICS LETTERS, 2022, 47 (19) : 5184 - 5187
  • [22] Multi Frame Super-Resolution for Versatile Video Coding
    Hori, Toshiya
    Yano, Remina
    Watanabe, Hiroshi
    Chujoh, Takeshi
    Ikai, Tomohiro
    Sasaki, Eiichi
    Suzuki, Takuya
    Ito, Norio
    INTERNATIONAL WORKSHOP ON ADVANCED IMAGING TECHNOLOGY (IWAIT) 2021, 2021, 11766
  • [23] Motion compensated super-resolution of video by level sets evolution
    Vázquez, C
    Aly, H
    Dubois, E
    Mitiche, A
    ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5, 2004, : 1767 - 1770
  • [24] TMP: Temporal Motion Propagation for Online Video Super-Resolution
    Zhang, Zhengqiang
    Li, Ruihuang
    Guo, Shi
    Cao, Yang
    Zhang, Lei
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2024, 33 : 5014 - 5028
  • [25] Video Super-Resolution Using Simultaneous Motion and Intensity Calculations
    Keller, Sune Hogild
    Lauze, Francois
    Nielsen, Mads
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (07) : 1870 - 1884
  • [26] LOCALLY ADAPTIVE REGULARIZED SUPER-RESOLUTION ON VIDEO WITH ARBITRARY MOTION
    Lee, I-Hsien
    Bose, Nirmal K.
    Lin, Chih-Wei
    2010 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, 2010, : 897 - 900
  • [27] A pioneering video super-resolution reconstruction without motion estimation
    Guo, Li
    He, Xiaohai
    Luo, Daisheng
    Teng, Qizhi
    Journal of Computational Information Systems, 2011, 7 (14): : 5058 - 5067
  • [28] SUPER-RESOLUTION OF VIDEO USING KEY FRAMES AND MOTION ESTIMATION
    Brandi, Fernanda
    de Queiroz, Ricardo
    Mukherjee, Debargha
    2008 15TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1-5, 2008, : 321 - 324
  • [29] Bidirectional scale-aware upsampling network for arbitrary-scale video super-resolution
    Luo, Laigan
    Yi, Benshun
    Wang, Zhongyuan
    He, Zheng
    Zhu, Chao
    IMAGE AND VISION COMPUTING, 2024, 148
  • [30] Learning a Deep Dual Attention Network for Video Super-Resolution
    Li, Feng
    Bai, Huihui
    Zhao, Yao
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 (29) : 4474 - 4488