Deep Hyperspectral Prior: Single-Image Denoising, Inpainting, Super-Resolution
Chapter
Accepted version
Åpne
Permanent lenke
https://hdl.handle.net/11250/2651786Utgivelsesdato
2019Metadata
Vis full innførselSamlinger
Originalversjon
10.1109/ICCVW.2019.00477Sammendrag
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.