Hybrid-Domain Synergistic Transformer for Hyperspectral Image Denoising

TL;DR

This paper introduces a novel hyperspectral image denoising framework called HDST that leverages frequency domain enhancement and multiscale modeling to effectively suppress complex noise while preserving details.

Contribution

It proposes a hybrid-domain synergistic transformer network with frequency domain preprocessing, cross-domain attention, and hierarchical architecture for improved hyperspectral image denoising.

Findings

Significantly outperforms existing methods on real and synthetic datasets.

Effectively captures cross-band correlations and spectral noise components.

Maintains computational efficiency while enhancing denoising performance.

Abstract

Hyperspectral image denoising faces the challenge of multi-dimensional coupling of spatially non-uniform noise and spectral correlation interference. Existing deep learning methods mostly focus on RGB images and struggle to effectively handle the unique spatial-spectral characteristics and complex noise distributions of hyperspectral images (HSI). This paper proposes an HSI denoising framework, Hybrid-Domain Synergistic Transformer Network (HDST), based on frequency domain enhancement and multiscale modeling, achieving three-dimensional collaborative processing of spatial, frequency and channel domains. The method innovatively integrates three key mechanisms: (1) introducing an FFT preprocessing module with multi-band convolution to extract cross-band correlations and decouple spectral noise components; (2) designing a dynamic cross-domain attention module that adaptively fuses spatial domain texture features and frequency domain noise priors through a learnable gating mechanism; (3) building a hierarchical architecture where shallow layers capture global noise statistics using multiscale atrous convolution, and deep layers achieve detail recovery through frequency domain postprocessing. Experiments on both real and synthetic datasets demonstrate that HDST significantly improves denoising performance while maintaining computational efficiency, validating the effectiveness of the proposed method. This research provides new insights and a universal framework for addressing complex noise coupling issues in HSI and other high-dimensional visual data. The code is available at https://github.com/lhy-cn/HDST-HSIDenoise.