Exploiting Frequency Correlation for Hyperspectral Image Reconstruction

TL;DR

This paper introduces a novel hyperspectral image reconstruction method that exploits frequency correlation priors and combines frequency and space domain learning via a transformer, achieving superior results.

Contribution

It proposes a new frequency correlation prior and a hybrid transformer model that integrates frequency domain learning with existing space domain methods for improved HSI reconstruction.

Findings

Outperforms state-of-the-art methods in reconstruction quality.

Enhances computational efficiency in hyperspectral image reconstruction.

Effectively exploits frequency priors for better image detail recovery.

Abstract

Deep priors have emerged as potent methods in hyperspectral image (HSI) reconstruction. While most methods emphasize space-domain learning using image space priors like non-local similarity, frequency-domain learning using image frequency priors remains neglected, limiting the reconstruction capability of networks. In this paper, we first propose a Hyperspectral Frequency Correlation (HFC) prior rooted in in-depth statistical frequency analyses of existent HSI datasets. Leveraging the HFC prior, we subsequently establish the frequency domain learning composed of a Spectral-wise self-Attention of Frequency (SAF) and a Spectral-spatial Interaction of Frequency (SIF) targeting low-frequency and high-frequency components, respectively. The outputs of SAF and SIF are adaptively merged by a learnable gating filter, thus achieving a thorough exploitation of image frequency priors. Integrating the frequency domain learning and the existing space domain learning, we finally develop the Correlation-driven Mixing Domains Transformer (CMDT) for HSI reconstruction. Extensive experiments highlight that our method surpasses various state-of-the-art (SOTA) methods in reconstruction quality and computational efficiency.