Efficient learning-based image enhancement:application to super-resolution and compression artifact removal

Kwon, Younghee and Kim, Kwang In and Kim, Jin H. and Theobalt, Christian (2012) Efficient learning-based image enhancement:application to super-resolution and compression artifact removal. In: Proc. British Machine Vision Conference (BMVC) 2012. UNSPECIFIED, 14.1-14.12.

[img]
Preview
PDF (\\lancs\homes\60\zhangy3\My Desktop\PURE PDF\efficient)
efficient.pdf - Submitted Version

Download (1MB)

Abstract

In this paper, we describe a framework for learning-based image enhancement. At the core of our algorithm lies a generic regularization framework that comprises a prior on natural images, as well as an application-specific conditional model based on Gaussian processes. In contrast to prior learning-based approaches, our algorithm can instantly learn task-specific degradation models from sample images which enables users to easily adopt the algorithm to a specific problem and data set of interest. This is facilitated by our efficient approximation scheme of large-scale Gaussian processes. We demonstrate the efficiency and effectiveness of our approach by applying it to two example enhancement applications: single-image super-resolution as well as artifact removal in JPEG-encoded images.

Item Type:
Contribution in Book/Report/Proceedings
ID Code:
69852
Deposited By:
Deposited On:
02 Jul 2014 09:28
Refereed?:
Yes
Published?:
Published
Last Modified:
06 Jul 2020 23:35