Initial image selection and its influence on super-resolution reconstruction

Shen Minmin*, Wang Ci, Xue Ping, Lin Weisi

*Corresponding author for this work

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

Abstract

Super-resolution (SR) reconstruction is a technique to yield a higher resolution (HR) image from aliasing low resolution (LR) ones. An LR image is upsampled as the initialization, and then iteratively corrected in comparison with the other LR images. As the solution satisfying the SR constraints is non-unique, it is impossible to recover the original HR details completely by SR techniques. The solution reconstructed is sensitive to the starting point, especially when LR observations are insufficient, and may converge to a local optimum point. SR images reconstructed with different initializations may diverge in different ways from the true HR image. The influence of the initial HR estimate has not been sufficiently addressed so far by existing SR methods. We will explore this initial image selection issue to improve the performance of SR reconstruction.

Original languageEnglish
Title of host publication2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings
Pages86-89
Number of pages4
DOIs
StatePublished - 2007
Externally publishedYes
Event2007 IEEE Workshop on Signal Processing Systems, SiPS 2007 - Shanghai, China
Duration: 17 Oct 200719 Oct 2007

Publication series

NameIEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
ISSN (Print)1520-6130

Conference

Conference2007 IEEE Workshop on Signal Processing Systems, SiPS 2007
Country/TerritoryChina
CityShanghai
Period17/10/0719/10/07

Keywords

  • Performance bound
  • SR

Fingerprint

Dive into the research topics of 'Initial image selection and its influence on super-resolution reconstruction'. Together they form a unique fingerprint.

Cite this