Long-Term Video Generation with Evolving Residual Video Frames

Nayoung Kim, Je Won Kang

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

4 Scopus citations

Abstract

In this paper, we propose a novel long-term video generation algorithm, motivated by the recent developments of unsupervised deep learning techniques. The proposed technique learns two ingredients of internal video representation, i.e., video textures and motions to reproduce realistic pixels in the future video frames. To this aim, the proposed technique uses two encoders comprising convolutional neural networks (CNN) to extract spatiotemporal features from the original video frame and a residual video frame, respectively. The use of the residual frame facilitates the learning with fewer parameters as there are high spatiotemporal correlations in a video. Moreover, the residual frames are efficiently used for evolving pixel differences in the future frame. In a decoder, the future frame is generated by transforming the combination of two feature vectors into the original video size. Experimental results demonstrate that the proposed technique provides more robust and accurate results of long-term video generation than conventional techniques.

Original languageEnglish
Title of host publication2018 IEEE International Conference on Image Processing, ICIP 2018 - Proceedings
PublisherIEEE Computer Society
Pages3578-3582
Number of pages5
ISBN (Electronic)9781479970612
DOIs
StatePublished - 29 Aug 2018
Event25th IEEE International Conference on Image Processing, ICIP 2018 - Athens, Greece
Duration: 7 Oct 201810 Oct 2018

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Conference

Conference25th IEEE International Conference on Image Processing, ICIP 2018
Country/TerritoryGreece
CityAthens
Period7/10/1810/10/18

Keywords

  • Convolutional neural network
  • Future video prediction
  • Unsupervised learning
  • Video generation

Fingerprint

Dive into the research topics of 'Long-Term Video Generation with Evolving Residual Video Frames'. Together they form a unique fingerprint.

Cite this