Please use this identifier to cite or link to this item: http://hdl.handle.net/1959.13/927296

OpenURL Link
Title
Learning priors for super-resolution in video sequence
Author/Creator
Peng, Yu;  Jin, Jesse S.;  Luo, Suhuai;  Xu, Min
Institution
The University of Newcastle. Faculty of Science & Information Technology, School of Design, Communication and Information Technology
Description
Video becomes a crucial information resource in last decades, because of the rapid development of camera as well as the internet explosion. High-quality video sequences are always desired in lots of fields. Since the bottleneck of data storage and interferences of shooting condition, we cannot always obtain high-resolution video. This botheration can be circumvented by super-resolution. Currently, almost super-resolution techniques are in the framework of Maximum a Posterior (MAP). Appropriate parameters of prior distribution are crucial for recovering accurate super-resolution image. We utilise a novel Weighted Cross Validation (WCG) method to learn theses prior parameters. Comparison experiments are provided to illustrate the effectiveness of our approach.
Relation
2nd International Conference on Internet Multimedia Computing and Service (ICIMCS 2010). ICIMCS '10: Proceedings of the Second International Conference on Internet Multimedia Computing and Service (Harbin, China 30-31 December, 2010) p. 163-166
Publisher Link
http://dx.doi.org/10.1145/1937728.1937767
Date
2010
Publisher
ACM
Keyword(s)
super-resolution;  prior distribution;  weighted cross validation
Resource Type
conference paper
Identifier
http://hdl.handle.net/1959.13/927296
Identifier
ISBN:9781450304603
Reviewed
Reviewed
13 Visitors 14 Hits 0 Downloads
Save/E-mail Citation
Citation Format
E-mail Address
Subject
"Learning priors for super-resolution in video sequence"
 
OR