Hyperspectral Super-Resolution by Unsupervised Convolutional Neural Network and Sure

Han V. Nguyen, Magnus O. Ulfarsson, Johannes R. Sveinsson, Mauro Dalla Mura

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent advances in deep learning (DL) reveal that the structure of a convolutional neural network (CNN) is a good image prior (called deep image prior (DIP)), bridging the model-based and DL-based methods in image restoration. However, optimizing a DIP-based CNN is prone to over-fitting leading to a poorly reconstructed image. This paper derives a loss function based on Stein's unbiased risk estimate (SURE) for unsupervised training of a DIP-based CNN applied to the hyperspectral image (HSI) super-resolution. The SURE loss function is an unbiased estimate of the mean-square-error (MSE) between the clean low-resolution image and the low-resolution estimated image, which relies only on the observed low-resolution image. Experimental results on HSI show that the proposed method not only improves the performance, but also avoids overfitting. Codes are available at https://github.com/hvn2/SURE-MS-HS

Original languageEnglish
Title of host publicationIGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages903-906
Number of pages4
ISBN (Electronic)9781665427920
DOIs
Publication statusPublished - 17 Jul 2022
Event2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022 - Kuala Lumpur, Malaysia
Duration: 17 Jul 202222 Jul 2022

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2022-July

Conference

Conference2022 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2022
Country/TerritoryMalaysia
CityKuala Lumpur
Period17/07/2222/07/22

Bibliographical note

Funding Information: This work was supported in part by the University of Iceland Doctoral Fund under Grant 1547-15430, and the Icelandic Research Fund under Grant 207233-051. Publisher Copyright: © 2022 IEEE.

Other keywords

  • Hyperspectral image
  • Stein's unbiased risk estimate (SURE)
  • image fusion
  • unsupervised CNN

Fingerprint

Dive into the research topics of 'Hyperspectral Super-Resolution by Unsupervised Convolutional Neural Network and Sure'. Together they form a unique fingerprint.

Cite this