Video super-resolution using wave-shape network

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Video super-resolution (VSR) aims to restore a high-resolution (HR) image from multiple low-resolution (LR) frames. Previous works deal with inputs LR frames by stacking or warping and only use single scale features for reconstruction. Most of them didn't consider fusing multi-scale spatial and inter-frame temporal information, which may result in loss of details. In this paper, a novel architecture named Wave-shape network is proposed, which is designed to treat each frame as a separate source of information and fuse different temporal frames through a multi-scale structure. This fusion strategy enables us to capture more complete structure and context information for HR image quality improvement. We evaluate this model on Vid4 dataset and the results show Waveshape network not only achieves significant improvement in vision but also obtains much higher PSNR and SSIM than most previous VSR methods.

Original languageEnglish
Title of host publicationProceedings of the 2019 3rd International Conference on Video and Image Processing, ICVIP 2019
PublisherAssociation for Computing Machinery
Number of pages5
ISBN (Electronic)9781450376822
Publication statusPublished - 2019 Dec 20
Event3rd International Conference on Video and Image Processing, ICVIP 2019 - Shanghai, China
Duration: 2019 Dec 202019 Dec 23

Publication series

NameACM International Conference Proceeding Series


Conference3rd International Conference on Video and Image Processing, ICVIP 2019


  • Convolution neural network
  • Multi-scale feature fusion
  • Video super-resolution
  • Wave-shape network

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications


Dive into the research topics of 'Video super-resolution using wave-shape network'. Together they form a unique fingerprint.

Cite this