A Review of Hyperspectral Image Super-Resolution Based on Deep Learning
Hyperspectral image (HSI) super-resolution (SR) is a classical computer vision task that aims to accomplish the conversion of images from lower to higher resolutions. With the booming development of deep learning (DL) technology, more and more researchers are dedicated to the research of image SR te...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/11/2853 |
| _version_ | 1827739227949891584 |
|---|---|
| author | Chi Chen Yongcheng Wang Ning Zhang Yuxi Zhang Zhikang Zhao |
| author_facet | Chi Chen Yongcheng Wang Ning Zhang Yuxi Zhang Zhikang Zhao |
| author_sort | Chi Chen |
| collection | DOAJ |
| description | Hyperspectral image (HSI) super-resolution (SR) is a classical computer vision task that aims to accomplish the conversion of images from lower to higher resolutions. With the booming development of deep learning (DL) technology, more and more researchers are dedicated to the research of image SR techniques based on DL and have made remarkable progress. However, no scholar has provided a comprehensive review of the field. As a response, in this paper we aim to supply a comprehensive summary of the DL-based SR techniques for HSI, including upsampling frameworks, upsampling methods, network design, loss functions, representative works with different strategies, and future directions, in which we design several sets of comparative experiments for the advantages and limitations of two-dimensional convolution and three-dimensional convolution in the field of HSI SR and analyze the experimental results in depth. In addition, the paper also briefly discusses the secondary foci such as common datasets, evaluation metrics, and traditional SR algorithms. To the best of our knowledge, this paper is the first review on DL-based HSI SR. |
| first_indexed | 2024-03-11T02:57:51Z |
| format | Article |
| id | doaj.art-9d35c4e32f4646008f008950a4c59bc8 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T02:57:51Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9d35c4e32f4646008f008950a4c59bc82023-11-18T08:29:37ZengMDPI AGRemote Sensing2072-42922023-05-011511285310.3390/rs15112853A Review of Hyperspectral Image Super-Resolution Based on Deep LearningChi Chen0Yongcheng Wang1Ning Zhang2Yuxi Zhang3Zhikang Zhao4Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaDepartment of Electronic Engineering, Tsinghua University, Beijing 100084, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaChangchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaHyperspectral image (HSI) super-resolution (SR) is a classical computer vision task that aims to accomplish the conversion of images from lower to higher resolutions. With the booming development of deep learning (DL) technology, more and more researchers are dedicated to the research of image SR techniques based on DL and have made remarkable progress. However, no scholar has provided a comprehensive review of the field. As a response, in this paper we aim to supply a comprehensive summary of the DL-based SR techniques for HSI, including upsampling frameworks, upsampling methods, network design, loss functions, representative works with different strategies, and future directions, in which we design several sets of comparative experiments for the advantages and limitations of two-dimensional convolution and three-dimensional convolution in the field of HSI SR and analyze the experimental results in depth. In addition, the paper also briefly discusses the secondary foci such as common datasets, evaluation metrics, and traditional SR algorithms. To the best of our knowledge, this paper is the first review on DL-based HSI SR.https://www.mdpi.com/2072-4292/15/11/2853super-resolutionhyperspectral imagedeep learningconvolutional neural networks (CNNs)generative adversarial networks (GANs) |
| spellingShingle | Chi Chen Yongcheng Wang Ning Zhang Yuxi Zhang Zhikang Zhao A Review of Hyperspectral Image Super-Resolution Based on Deep Learning Remote Sensing super-resolution hyperspectral image deep learning convolutional neural networks (CNNs) generative adversarial networks (GANs) |
| title | A Review of Hyperspectral Image Super-Resolution Based on Deep Learning |
| title_full | A Review of Hyperspectral Image Super-Resolution Based on Deep Learning |
| title_fullStr | A Review of Hyperspectral Image Super-Resolution Based on Deep Learning |
| title_full_unstemmed | A Review of Hyperspectral Image Super-Resolution Based on Deep Learning |
| title_short | A Review of Hyperspectral Image Super-Resolution Based on Deep Learning |
| title_sort | review of hyperspectral image super resolution based on deep learning |
| topic | super-resolution hyperspectral image deep learning convolutional neural networks (CNNs) generative adversarial networks (GANs) |
| url | https://www.mdpi.com/2072-4292/15/11/2853 |
| work_keys_str_mv | AT chichen areviewofhyperspectralimagesuperresolutionbasedondeeplearning AT yongchengwang areviewofhyperspectralimagesuperresolutionbasedondeeplearning AT ningzhang areviewofhyperspectralimagesuperresolutionbasedondeeplearning AT yuxizhang areviewofhyperspectralimagesuperresolutionbasedondeeplearning AT zhikangzhao areviewofhyperspectralimagesuperresolutionbasedondeeplearning AT chichen reviewofhyperspectralimagesuperresolutionbasedondeeplearning AT yongchengwang reviewofhyperspectralimagesuperresolutionbasedondeeplearning AT ningzhang reviewofhyperspectralimagesuperresolutionbasedondeeplearning AT yuxizhang reviewofhyperspectralimagesuperresolutionbasedondeeplearning AT zhikangzhao reviewofhyperspectralimagesuperresolutionbasedondeeplearning |