Presentation 2008-03-13
Bayesian Image Superresolution under Moving Occlusion
Wataru FUKUDA, Shin-ichi MAEDA, Atsunori KANEMURA, Shin ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We deal with image super-resolution that estimates the high resolution image from more than two observed images. In this study, we focus on the image super-resolution problem when the observation noise moves. In the existing studies, noise processes have been assumed to be uniform or fixed. However, it is more plausible to assume the presence of moving noise or moving occlusion when a sequence of video images are taken. For example, satellite images can be occluded by clouds in the sky, clean shots can be obstructed by people at a tourist site, etc. Experiments show that our super-resolution method better performs than the other existing methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image superresolution / variational EM algorithm / spin glasses / moving occlusion
Paper # NC2007-152
Date of Issue

Conference Information
Committee NC
Conference Date 2008/3/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Bayesian Image Superresolution under Moving Occlusion
Sub Title (in English)
Keyword(1) Image superresolution
Keyword(2) variational EM algorithm
Keyword(3) spin glasses
Keyword(4) moving occlusion
1st Author's Name Wataru FUKUDA
1st Author's Affiliation Faculty of Engineering, Kyoto University()
2nd Author's Name Shin-ichi MAEDA
2nd Author's Affiliation Graduate School of Information Science Nara Institute of Science and Technology
3rd Author's Name Atsunori KANEMURA
3rd Author's Affiliation Faculty of Engineering, Kyoto University
4th Author's Name Shin ISHII
4th Author's Affiliation Faculty of Engineering, Kyoto University
Date 2008-03-13
Paper # NC2007-152
Volume (vol) vol.107
Number (no) 542
Page pp.pp.-
#Pages 6
Date of Issue