Key frame-based video super-resolution using bi-directional overlapped block motion compensation and trained dictionary

Byung Cheal Song, Shin Cheal Jeong, Yanglim Choi

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

4 Scopus citations

Abstract

This paper presents a video super-resolution algorithm to interpolate an arbitrary frame in a low resolution video sequence from sparsely existing high resolution key pictures. Firstly, hierarchical motion estimation is performed between the input and the key low resolution frames on a patch basis. If motion-compensated error is small, an input LR patch is super-resolved by bi-directional overlapped block motion compensation. Otherwise, the input patch is spatially super-resolved using the dictionary which is learned from the key low resolution and its corresponding high resolution pictures beforehand. Finally, possible blocking artifacts between a motion-compensated patch and a spatially super-resolved patch are concealed using a specific de-blocking process. Experimental results show that the proposed algorithm provides significantly better subjective visual quality as well as objective quality than previous interpolation algorithms.

Original languageEnglish
Title of host publication2010 2nd International Conference on Image Processing Theory, Tools and Applications, IPTA 2010
Pages181-186
Number of pages6
DOIs
StatePublished - 2010
Event2010 2nd International Conference on Image Processing Theory, Tools and Applications, IPTA 2010 - Paris, France
Duration: 7 Jul 201010 Jul 2010

Publication series

Name2010 2nd International Conference on Image Processing Theory, Tools and Applications, IPTA 2010

Conference

Conference2010 2nd International Conference on Image Processing Theory, Tools and Applications, IPTA 2010
Country/TerritoryFrance
CityParis
Period7/07/1010/07/10

Keywords

  • Bi-directional overlapped block motion-compensation
  • Dictionary
  • Hierarchical motion estimation
  • Key pictures
  • Super-resolution
  • Training

Fingerprint

Dive into the research topics of 'Key frame-based video super-resolution using bi-directional overlapped block motion compensation and trained dictionary'. Together they form a unique fingerprint.

Cite this