Skip to main navigation Skip to search Skip to main content

Video frame interpolation based on multi-scale convolutional network and adversarial training

  • School of Computer Science and Technology, Harbin Institute of Technology
  • Nanjing General Hospital

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a deep multi-scale convolutional neural network solution for video frame interpolation, which can synthesize the interpolated frames with favorable quality and visual experience. To get sharp results, we use a combination of loss function, including a Wasserstein generative adversarial network loss with gradient penalty. We try a slim generator network structure in order to meet the real-time interpolation requirement as much as possible. In this way our framework contains less parameters, which could be beneficial to video processing tasks in future works. Our work is also shown to be effective in improving subjective visual experience for video frames in most cases.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE 3rd International Conference on Data Science in Cyberspace, DSC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages553-560
Number of pages8
ISBN (Electronic)9781538642108
DOIs
StatePublished - 16 Jul 2018
Externally publishedYes
Event3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018 - Guangzhou, Guangdong, China
Duration: 18 Jun 201821 Jun 2018

Publication series

NameProceedings - 2018 IEEE 3rd International Conference on Data Science in Cyberspace, DSC 2018

Conference

Conference3rd IEEE International Conference on Data Science in Cyberspace, DSC 2018
Country/TerritoryChina
CityGuangzhou, Guangdong
Period18/06/1821/06/18

Keywords

  • Adversarial training
  • Deep learning
  • Frame synthesis
  • Multi-scale
  • Video frame interpolation

Fingerprint

Dive into the research topics of 'Video frame interpolation based on multi-scale convolutional network and adversarial training'. Together they form a unique fingerprint.

Cite this