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

TL;DR

This paper introduces a novel deep learning model, HSID-CNN, that effectively denoises hyperspectral images by leveraging combined spatial and spectral features through multi-scale and multi-level feature extraction, outperforming existing methods.

Contribution

The paper presents a new end-to-end deep convolutional neural network that simultaneously exploits spatial and spectral information for hyperspectral image denoising, with multi-scale and multi-level features.

Findings

Outperforms mainstream denoising methods in quantitative metrics

Improves visual quality of hyperspectral images

Enhances HSI classification accuracy

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.