Hyperspectral Image Denoising Employing a Spatial-Spectral Deep Residual Convolutional Neural Network

Abstract

Hyperspectral image (HSI) denoising is a crucial preprocessing procedure to improve the performance of the subsequent HSI interpretation and applications. In this paper, a novel deep learning-based method for this task is proposed, by learning a non-linear end-to-end mapping between the noisy and clean HSIs with a combined spatial-spectral deep convolutional neural network (HSID-CNN). Both the spatial and spectral information are simultaneously assigned to the proposed network. In addition, multi-scale feature extraction and multi-level feature representation are respectively employed to capture both the multi-scale spatial-spectral feature and fuse the feature representations with different levels for the final restoration. The simulated and real-data experiments demonstrate that the proposed HSID-CNN outperforms many of the mainstream methods in both the quantitative evaluation indexes, visual effects, and HSI classification accuracy.

arXiv commentAccepted by IEEE TGRS, available codes: https://github.com/WHUQZhang/HSID-CNN

References in corpus (9)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Deep learning in remote sensing: a review
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification
• Exploring Models and Data for Remote Sensing Image Caption Generation
• Boosting the accuracy of multi-spectral image pan-sharpening by learning a deep residual network
• Missing Data Reconstruction in Remote Sensing image with a Unified Spatial-Temporal-Spectral Deep Convolutional Neural Network
• Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

Cited by in corpus (36)

• Hybrid Noise Removal in Hyperspectral Imagery With a Spatial-Spectral Gradient Network
• Image Restoration for Remote Sensing: Overview and Toolbox
• High-throughput molecular imaging via deep learning enabled Raman spectroscopy
• Spatial-Spectral Fusion by Combining Deep Learning and Variation Model
• Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
• Fast Noise Removal in Hyperspectral Images via Representative Coefficient Total Variation
• Deep Plug-and-Play Prior for Hyperspectral Image Restoration
• Hyperspectral Denoising Using Unsupervised Disentangled Spatio-Spectral Deep Priors
• Lightweight Modules for Efficient Deep Learning based Image Restoration
• Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks
• Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization
• Connections between Deep Equilibrium and Sparse Representation Models with Application to Hyperspectral Image Denoising
• Nonlocal Patch-Based Fully-Connected Tensor Network Decomposition for Remote Sensing Image Inpainting
• Hyperspectral Image Denoising via Spatial-Spectral Recurrent Transformer
• Deep Learning on Image Denoising: An overview
• Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration
• Deep Hyperspectral Prior: Denoising, Inpainting, Super-Resolution
• Riesz-Quincunx-UNet Variational Auto-Encoder for Satellite Image Denoising
• Low-Light Hyperspectral Image Enhancement
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
• A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods
• HyDe: The First Open-Source, Python-Based, GPU-Accelerated Hyperspectral Denoising Package
• Unsupervised Denoising for Satellite Imagery using Wavelet Subband CycleGAN
• Iterative Low-rank Network for Hyperspectral Image Denoising
• 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising
• Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising
• H2TF for Hyperspectral Image Denoising: Where Hierarchical Nonlinear Transform Meets Hierarchical Matrix Factorization
• Spectral Response Function Guided Deep Optimization-driven Network for Spectral Super-resolution
• Constrained low-tubal-rank tensor recovery for hyperspectral images mixed noise removal by bilateral random projections
• Uncertainty Quantification for Hyperspectral Image Denoising Frameworks based on Low-rank Matrix Approximation
• ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising
• SSCAN: A Spatial-spectral Cross Attention Network for Hyperspectral Image Denoising
• Multispectral CT Denoising via Simulation-Trained Deep Learning: Experimental Results at the ESRF BM18
• Hyperspectral Image Denoising with Partially Orthogonal Matrix Vector Tensor Factorization
• Unsupervised Hyperspectral Mixed Noise Removal Via Spatial-Spectral Constrained Deep Image Prior
• Hyperspectral Image Classification Based on Adaptive Sparse Deep Network