An improved style transfer approach for videos

Rong Jie Chang, Chin Chen Chang, Der Lor Way, Zen-Chung Shih

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

Abstract

In this paper, we present an improved approach to transfer style for videos based on semantic segmentation. We segment foreground objects and background, and then apply different styles respectively. A fully convolutional neural network is used to perform semantic segmentation. We increase the reliability of the segmentation, and use the information of segmentation and the relationship between foreground objects and background to improve segmentation iteratively. We also use segmentation to improve optical flow, and apply different motion estimation methods between foreground objects and background. This improves the motion boundaries of optical flow, and solves the problems of incorrect and discontinuous segmentation caused by occlusion and shape deformation.

Original languageEnglish
Title of host publication2018 International Workshop on Advanced Image Technology, IWAIT 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-2
Number of pages2
ISBN (Electronic)9781538626153
DOIs
StatePublished - 30 May 2018
Event2018 International Workshop on Advanced Image Technology, IWAIT 2018 - Chiang Mai, Thailand
Duration: 7 Jan 20189 Jan 2018

Publication series

Name2018 International Workshop on Advanced Image Technology, IWAIT 2018

Conference

Conference2018 International Workshop on Advanced Image Technology, IWAIT 2018
CountryThailand
CityChiang Mai
Period7/01/189/01/18

Keywords

  • Motion estimation
  • Neural network
  • Semantic segmentation
  • Style transfer

Fingerprint Dive into the research topics of 'An improved style transfer approach for videos'. Together they form a unique fingerprint.

Cite this