Dense Correspondence Estimation for Image Interpolation Christian Linz, Marcus Magnor

Christian Linz and Marcus Magnor: "Dense Correspondence Estimation for Image Interpolation", Technical Report no. 13, Computer Graphics Lab, TU Braunschweig, November 2010. http://www.digibib.tu-bs.de/?docid=00036631 [pdf] [bib]

Abstract

We evaluate the current state-of-the-art in dense correspondence estimation
for the use in multi-image interpolation algorithms. The evaluation is carried
out on three real-world scenes and one synthetic scene, each featuring varying
challenges for dense correspondence estimation. The primary focus of
our study is on the perceptual quality of the interpolation sequences created
from the estimated flow fields. Perceptual plausibility is assessed by means
of a psychophysical user study. Our results show that current state-of-the-art
in dense correspondence estimation does not produce visually plausible
interpolations.

TU Braunschweig - Fakultät für Mathematik und Informatik - Computer Graphics - Publications - Dense Correspondence Estimation for Image Interpolation