Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning

Hyperspectral image (HSI) super-resolution (SR) in both spatial and spectral dimensions is one of the most attractive research topics in HSI processing. Although recent advances in deep learning (DL) frameworks have greatly improved the performance of spatial-spectral SR reconstruction, existing met...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanan Zhang, Jizhou Zhang, Sijia Han
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10521696/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707692089671680
author Yanan Zhang
Jizhou Zhang
Sijia Han
author_facet Yanan Zhang
Jizhou Zhang
Sijia Han
author_sort Yanan Zhang
collection DOAJ
description Hyperspectral image (HSI) super-resolution (SR) in both spatial and spectral dimensions is one of the most attractive research topics in HSI processing. Although recent advances in deep learning (DL) frameworks have greatly improved the performance of spatial-spectral SR reconstruction, existing methods learn discrete representations of HSI, ignoring real-world signals' continuous nature. Recently, Implicit Neural Representation (INR) has been applied to 3D surface reconstruction and image SR for continuous representation and has attracted increasing attention. In this paper, we propose the Local Implicit Spatial-spectral Function (LISSF), which learns a local continuous representation of high spatial resolution hyperspectral images (HR-HSI) from the discrete inputs. The model consists of a deep feature encoder and a spatial-spectral intensity decoder. The encoder converts the low spatial resolution multispectral image (LR-MSI) into deep features and the decoder predicts the intensity values at the given coordinates as output. Since the spatial-spectral coordinates are continuous, LISSF can achieve spatial-spectral SR in arbitrary scales, even extrapolating to higher resolutions not covered by the training data. Extensive experiments on spatial-spectral SR, spatial SR, and spectral SR demonstrate that LISSF can achieve superior performance in comparison with state-of-the-art methods. Moreover, ablation studies are performed on the effects of individual components of LISSF.
format Article
id doaj-art-fe57701be8cf4fc998ebd76ec4705c8e
institution DOAJ
issn 1943-0655
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-fe57701be8cf4fc998ebd76ec4705c8e2025-08-20T03:15:51ZengIEEEIEEE Photonics Journal1943-06552024-01-0116311210.1109/JPHOT.2024.339723210521696Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function LearningYanan Zhang0https://orcid.org/0009-0004-8129-6516Jizhou Zhang1Sijia Han2School of Arts and Media, Hubei Business College, Wuhan, ChinaMech-Mind Robotics Technologies Ltd., Beijing, ChinaLaboratory of Microwave Sensing, National Space Science Center, Chinese Academy of Science, Beijing, ChinaHyperspectral image (HSI) super-resolution (SR) in both spatial and spectral dimensions is one of the most attractive research topics in HSI processing. Although recent advances in deep learning (DL) frameworks have greatly improved the performance of spatial-spectral SR reconstruction, existing methods learn discrete representations of HSI, ignoring real-world signals' continuous nature. Recently, Implicit Neural Representation (INR) has been applied to 3D surface reconstruction and image SR for continuous representation and has attracted increasing attention. In this paper, we propose the Local Implicit Spatial-spectral Function (LISSF), which learns a local continuous representation of high spatial resolution hyperspectral images (HR-HSI) from the discrete inputs. The model consists of a deep feature encoder and a spatial-spectral intensity decoder. The encoder converts the low spatial resolution multispectral image (LR-MSI) into deep features and the decoder predicts the intensity values at the given coordinates as output. Since the spatial-spectral coordinates are continuous, LISSF can achieve spatial-spectral SR in arbitrary scales, even extrapolating to higher resolutions not covered by the training data. Extensive experiments on spatial-spectral SR, spatial SR, and spectral SR demonstrate that LISSF can achieve superior performance in comparison with state-of-the-art methods. Moreover, ablation studies are performed on the effects of individual components of LISSF.https://ieeexplore.ieee.org/document/10521696/Hyperspectral image (HSI)spatial-spectral super-resolutionimplicit neural representations (INR)local implicit spatial-spectral function (LISSF)
spellingShingle Yanan Zhang
Jizhou Zhang
Sijia Han
Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
IEEE Photonics Journal
Hyperspectral image (HSI)
spatial-spectral super-resolution
implicit neural representations (INR)
local implicit spatial-spectral function (LISSF)
title Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
title_full Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
title_fullStr Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
title_full_unstemmed Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
title_short Hyperspectral Image Joint Super-Resolution via Local Implicit Spatial-Spectral Function Learning
title_sort hyperspectral image joint super resolution via local implicit spatial spectral function learning
topic Hyperspectral image (HSI)
spatial-spectral super-resolution
implicit neural representations (INR)
local implicit spatial-spectral function (LISSF)
url https://ieeexplore.ieee.org/document/10521696/
work_keys_str_mv AT yananzhang hyperspectralimagejointsuperresolutionvialocalimplicitspatialspectralfunctionlearning
AT jizhouzhang hyperspectralimagejointsuperresolutionvialocalimplicitspatialspectralfunctionlearning
AT sijiahan hyperspectralimagejointsuperresolutionvialocalimplicitspatialspectralfunctionlearning