Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction

Hyperspectral image (HSI) reconstruction is a critical and indispensable step in spectral compressive imaging (CASSI) systems and directly affects our ability to capture high-quality images in dynamic environments. Recent research has increasingly focused on deep unfolding frameworks for HSI reconst...

Full description

Saved in:
Bibliographic Details
Main Authors: Xian-Hua Han, Jian Wang, Yen-Wei Chen
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850266733275774976
author Xian-Hua Han
Jian Wang
Yen-Wei Chen
author_facet Xian-Hua Han
Jian Wang
Yen-Wei Chen
author_sort Xian-Hua Han
collection DOAJ
description Hyperspectral image (HSI) reconstruction is a critical and indispensable step in spectral compressive imaging (CASSI) systems and directly affects our ability to capture high-quality images in dynamic environments. Recent research has increasingly focused on deep unfolding frameworks for HSI reconstruction, showing notable progress. However, these approaches have to break the optimization task into two sub-problems, solving them iteratively over multiple stages, which leads to large models and high computational overheads. This study presents a simple yet effective method that passes the degradation information (sensing mask) through a deep learning network to disentangle the degradation and the latent target’s representations. Specifically, we design a lightweight MLP block to capture non-local similarities and long-range dependencies across both spatial and spectral domains, and investigate an attention-based mask modelling module to achieve the spatial–spectral-adaptive degradation representationthat is fed to the MLP-based network. To enhance the information flow between MLP blocks, we introduce a multi-level fusion module and apply reconstruction heads to different MLP features for deeper supervision. Additionally, we combine the projection loss from compressive measurements with reconstruction loss to create a dual-domain loss, ensuring consistent optical detection during HS reconstruction. Experiments on benchmark HS datasets show that our method outperforms state-of-the-art approaches in terms of both reconstruction accuracy and efficiency, reducing computational and memory costs.
format Article
id doaj-art-e7de8b46821548099c15f226c7742f5e
institution OA Journals
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-e7de8b46821548099c15f226c7742f5e2025-08-20T01:54:04ZengMDPI AGSensors1424-82202024-11-012422736210.3390/s24227362Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image ReconstructionXian-Hua Han0Jian Wang1Yen-Wei Chen2Graduate School of Artificial Intelligence and Science, Rikkyo University, Tokyo 171-8501, JapanSchool of Information Science and Engineering, Shandong Normal University, Jinan 250358, ChinaCollege of Information Science and Engineering, Ritsumeikan University, Osaka 603-8577, JapanHyperspectral image (HSI) reconstruction is a critical and indispensable step in spectral compressive imaging (CASSI) systems and directly affects our ability to capture high-quality images in dynamic environments. Recent research has increasingly focused on deep unfolding frameworks for HSI reconstruction, showing notable progress. However, these approaches have to break the optimization task into two sub-problems, solving them iteratively over multiple stages, which leads to large models and high computational overheads. This study presents a simple yet effective method that passes the degradation information (sensing mask) through a deep learning network to disentangle the degradation and the latent target’s representations. Specifically, we design a lightweight MLP block to capture non-local similarities and long-range dependencies across both spatial and spectral domains, and investigate an attention-based mask modelling module to achieve the spatial–spectral-adaptive degradation representationthat is fed to the MLP-based network. To enhance the information flow between MLP blocks, we introduce a multi-level fusion module and apply reconstruction heads to different MLP features for deeper supervision. Additionally, we combine the projection loss from compressive measurements with reconstruction loss to create a dual-domain loss, ensuring consistent optical detection during HS reconstruction. Experiments on benchmark HS datasets show that our method outperforms state-of-the-art approaches in terms of both reconstruction accuracy and efficiency, reducing computational and memory costs.https://www.mdpi.com/1424-8220/24/22/7362hyperspectral image reconstructiondegradationsensing maskspatial–spectral modellinglong dependencyMLP network
spellingShingle Xian-Hua Han
Jian Wang
Yen-Wei Chen
Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
Sensors
hyperspectral image reconstruction
degradation
sensing mask
spatial–spectral modelling
long dependency
MLP network
title Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
title_full Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
title_fullStr Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
title_full_unstemmed Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
title_short Mask-Guided Spatial–Spectral MLP Network for High-Resolution Hyperspectral Image Reconstruction
title_sort mask guided spatial spectral mlp network for high resolution hyperspectral image reconstruction
topic hyperspectral image reconstruction
degradation
sensing mask
spatial–spectral modelling
long dependency
MLP network
url https://www.mdpi.com/1424-8220/24/22/7362
work_keys_str_mv AT xianhuahan maskguidedspatialspectralmlpnetworkforhighresolutionhyperspectralimagereconstruction
AT jianwang maskguidedspatialspectralmlpnetworkforhighresolutionhyperspectralimagereconstruction
AT yenweichen maskguidedspatialspectralmlpnetworkforhighresolutionhyperspectralimagereconstruction