Degradation Estimation Recurrent Neural Network With Local and Non-Local Priors for Compressive Spectral Imaging

In the coded aperture snapshot spectral imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3-D hyperspectral images (HSIs) from 2-D measurements. However, some noticeable gaps exist between the imaging model used in DUNs and the real CASSI im...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-15
Main Authors: Dong, Yubo, Gao, Dahua, Li, Yuyan, Shi, Guangming, Liu, Danhua
Format: Article
Language:English
Subjects:
Compressive spectral imaging
Computational efficiency
Computational modeling
Dark current
deep learning
deep unfolding networks (DUNs)
Degradation
Estimation
hyperspectral images (HSIs)
Hyperspectral imaging
Image reconstruction
Imaging
Neural networks
Noise level
Noise levels
Parameters
Recurrent neural networks
Sensors
Transformers
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the coded aperture snapshot spectral imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3-D hyperspectral images (HSIs) from 2-D measurements. However, some noticeable gaps exist between the imaging model used in DUNs and the real CASSI imaging process, such as the sensing error as well as photon and dark current noise, compromising the accuracy of solving the data subproblem and the prior subproblem in DUNs. To address this issue, we propose a degradation estimation network (DEN) to correct the imaging model used in DUNs by simultaneously estimating the sensing error and the noise level, thereby improving the performance of DUNs. Additionally, we propose an efficient local and non-local transformer (LNLT) to solve the prior subproblem, which not only effectively models local and non-local similarities but also reduces the computational cost of the window-based global multihead self-attention (MSA). Furthermore, we transform the DUN into a recurrent neural network (RNN) by sharing parameters of DNNs across stages, which not only allows DNN to be trained more adequately but also significantly reduces the number of parameters. The proposed DERNN-LNLT achieves state-of-the-art (SOTA) performance with fewer parameters on both simulation and real datasets (code: https://github.com/ShawnDong98/DERNN-LNLT ).
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3410272