Hyperspectral Image Denoising Based On Multi-Stream Denoising Network

TL;DR

This paper introduces a multi-stream neural network for blind hyperspectral image denoising, effectively estimating noise levels and improving image quality across various noise types and scales.

Contribution

The novel Multi-Stream Denoising Network (MSDNet) combines noise estimation and denoising subnetworks with multiscale fusion, advancing HSI denoising performance.

Findings

Outperforms four closely related methods in experiments

Robust noise level estimation improves denoising quality

Effective across different noise types and scales

Abstract

Hyperspectral images (HSIs) have been widely applied in many fields, such as military, agriculture, and environment monitoring. Nevertheless, HSIs commonly suffer from various types of noise during acquisition. Therefore, denoising is critical for HSI analysis and applications. In this paper, we propose a novel blind denoising method for HSIs based on Multi-Stream Denoising Network (MSDNet). Our network consists of the noise estimation subnetwork and denoising subnetwork. In the noise estimation subnetwork, a multiscale fusion module is designed to capture the noise from different scales. Then, the denoising subnetwork is utilized to obtain the final denoising image. The proposed MSDNet can obtain robust noise level estimation, which is capable of improving the performance of HSI denoising. Extensive experiments on HSI dataset demonstrate that the proposed method outperforms four closely related methods.