dc.contributor.author | Sidorov, Oleksii | |
dc.contributor.author | Hardeberg, Jon Yngve | |
dc.date.accessioned | 2020-04-21T07:53:41Z | |
dc.date.available | 2020-04-21T07:53:41Z | |
dc.date.created | 2020-03-25T10:33:08Z | |
dc.date.issued | 2019 | |
dc.identifier.isbn | 9781728150239 | |
dc.identifier.uri | https://hdl.handle.net/11250/2651786 | |
dc.description.abstract | Deep learning algorithms have demonstrated state-of-the-art performance in various tasks of image restoration. This was made possible through the ability of CNNs to learn from large exemplar sets. However, the latter becomes an issue for hyperspectral image processing where datasets commonly consist of just a few images. In this work, we propose a new approach to denoising, inpainting, and super-resolution of hyperspectral image data using intrinsic properties of a CNN without any training. The performance of the given algorithm is shown to be comparable to the performance of trained networks, while its application is not restricted by the availability of training data. This work is an extension of original "deep prior" algorithm to hyperspectral imaging domain and 3D-convolutional networks. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | Computer Vision Workshops (ICCV Workshops), International Conference on | |
dc.title | Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution | en_US |
dc.type | Chapter | en_US |
dc.description.version | acceptedVersion | en_US |
dc.source.pagenumber | 3844-3851 | en_US |
dc.identifier.doi | 10.1109/ICCVW.2019.00477 | |
dc.identifier.cristin | 1803404 | |
dc.description.localcode | © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | en_US |
cristin.ispublished | true | |
cristin.fulltext | postprint | |
cristin.qualitycode | 1 | |