Super-resolution Enhancement of Video

Christopher M. Bishop, Andrew Blake, Bhaskara Marthi
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, PMLR R4:25-32, 2003.

Abstract

We consider the problem of enhancing the resolution of video through the addition of perceptually plausible high frequency information. Our approach is based on a learned data set of image patches capturing the relationship between the middle and high spatial frequency bands of natural images. By introducing an appropriate prior distribution over such patches we can ensure consistency of static image regions across successive frames of the video, and also take account of object motion. A key concept is the use of the previously enhanced frame to provide part of the training set for super-resolution enhancement of the current frame. Our results show that a marked improvement in video quality can be achieved at reasonable computational cost.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR4-bishop03a, title = {Super-resolution Enhancement of Video}, author = {Bishop, Christopher M. and Blake, Andrew and Marthi, Bhaskara}, booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics}, pages = {25--32}, year = {2003}, editor = {Bishop, Christopher M. and Frey, Brendan J.}, volume = {R4}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r4/bishop03a/bishop03a.pdf}, url = {https://proceedings.mlr.press/r4/bishop03a.html}, abstract = {We consider the problem of enhancing the resolution of video through the addition of perceptually plausible high frequency information. Our approach is based on a learned data set of image patches capturing the relationship between the middle and high spatial frequency bands of natural images. By introducing an appropriate prior distribution over such patches we can ensure consistency of static image regions across successive frames of the video, and also take account of object motion. A key concept is the use of the previously enhanced frame to provide part of the training set for super-resolution enhancement of the current frame. Our results show that a marked improvement in video quality can be achieved at reasonable computational cost.}, note = {Reissued by PMLR on 01 April 2021.} }
Endnote
%0 Conference Paper %T Super-resolution Enhancement of Video %A Christopher M. Bishop %A Andrew Blake %A Bhaskara Marthi %B Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2003 %E Christopher M. Bishop %E Brendan J. Frey %F pmlr-vR4-bishop03a %I PMLR %P 25--32 %U https://proceedings.mlr.press/r4/bishop03a.html %V R4 %X We consider the problem of enhancing the resolution of video through the addition of perceptually plausible high frequency information. Our approach is based on a learned data set of image patches capturing the relationship between the middle and high spatial frequency bands of natural images. By introducing an appropriate prior distribution over such patches we can ensure consistency of static image regions across successive frames of the video, and also take account of object motion. A key concept is the use of the previously enhanced frame to provide part of the training set for super-resolution enhancement of the current frame. Our results show that a marked improvement in video quality can be achieved at reasonable computational cost. %Z Reissued by PMLR on 01 April 2021.
APA
Bishop, C.M., Blake, A. & Marthi, B.. (2003). Super-resolution Enhancement of Video. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R4:25-32 Available from https://proceedings.mlr.press/r4/bishop03a.html. Reissued by PMLR on 01 April 2021.

Related Material