Naive Bayes Super-Resolution Forest
Jordi Salvador (Technicolor)
Eduardo Pérez-Pellitero (Technicolor)
Proceedings of the IEEE International Conference on Computer Vision, 2015
Here you can find the manuscript, a qualitative comparison and the accompanying code!
Abstract
This paper presents a fast, high-performance method for super resolution with external learning. The first contribution leading to the excellent performance is a bimodal tree for clustering, which successfully exploits the antipodal invariance of the coarse-to-high-res mapping of natural image patches and provides scalability to finer partitions of the underlying coarse patch space. During training an ensemble of such bimodal trees is computed, providing different linearizations of the mapping. The second and main contribution is a fast inference algorithm, which selects the most suitable mapping function within the tree ensemble for each patch by adopting a Local Naive Bayes formulation. The experimental validation shows promising scalability properties that reflect the suitability of the proposed model, which may also be generalized to other tasks. The resulting method is beyond one order of magnitude faster and performs objectively and subjectively better than the current state of the art.
BibTeX
@inproceedings { Salvador2015,
author = {Salvador, J. and P\'erez-Pellitero, E.},
title = {{Naive Bayes Super-Resolution Forest}},
booktitle = {Proc. {IEEE} Int. Conf. on Computer Vision},
pages = {325-333},
year = {2015},
}
Code
By downloading this software, you agree to the terms and conditions set forth in the license agreement.
Legal note. Please note that this software belongs to Technicolor, and that you are about to download it from an external server. The software is not and will not be hosted on this blog. I do not hold rights on this software, and its use is conditioned by the license you shall find enclosed with it.
Click here to accept the license agreement and download the software.
