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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dong, Yubo, Gao, Dahua, Li, Yuyan, Shi, Guangming, Liu, Danhua
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913195763957760
author Dong, Yubo
Gao, Dahua
Li, Yuyan
Shi, Guangming
Liu, Danhua
author_facet Dong, Yubo
Gao, Dahua
Li, Yuyan
Shi, Guangming
Liu, Danhua
contents In the Coded Aperture Snapshot Spectral Imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3D hyperspectral images (HSIs) from 2D 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 Multi-head 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.
format Preprint
id arxiv_https___arxiv_org_abs_2311_08808
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Degradation Estimation Recurrent Neural Network with Local and Non-Local Priors for Compressive Spectral Imaging
Dong, Yubo
Gao, Dahua
Li, Yuyan
Shi, Guangming
Liu, Danhua
Image and Video Processing
In the Coded Aperture Snapshot Spectral Imaging (CASSI) system, deep unfolding networks (DUNs) have demonstrated excellent performance in recovering 3D hyperspectral images (HSIs) from 2D 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 Multi-head 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.
title Degradation Estimation Recurrent Neural Network with Local and Non-Local Priors for Compressive Spectral Imaging
topic Image and Video Processing
url https://arxiv.org/abs/2311.08808