Hybrid Spatial-spectral Neural Network for Hyperspectral Image Denoising

TL;DR

This paper introduces a hybrid neural network that combines CNN and Transformer features to effectively denoise hyperspectral images by capturing both local and non-local details while reducing computational costs.

Contribution

A novel hybrid spatial-spectral neural network with a dual-path design and a decoupling strategy for efficient hyperspectral image denoising.

Findings

Outperforms state-of-the-art methods in spatial and spectral reconstruction

Effectively captures local and non-local spatial details

Reduces computational complexity compared to existing models

Abstract

Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising. Moreover, deep learning methods employ complex spectral learning mechanisms, thus introducing large computation costs. To address these problems, we propose a hybrid spatial-spectral denoising network (HSSD), in which we design a novel hybrid dual-path network inspired by CNN and Transformer characteristics, leading to capturing both local and non-local spatial details while suppressing noise efficiently. Furthermore, to reduce computational complexity, we adopt a simple but effective decoupling strategy that disentangles the learning of space and spectral channels, where multilayer perception with few parameters is utilized to learn the global correlations among spectra. The synthetic and real experiments demonstrate that our proposed method outperforms state-of-the-art methods on spatial and spectral reconstruction. The code and details are available on https://github.com/HLImg/HSSD.