Pixel Adaptive Deep Unfolding Transformer for Hyperspectral Image Reconstruction

TL;DR

This paper introduces PADUT, a novel hyperspectral image reconstruction method that employs pixel adaptive descent, a spectral transformer, and FFT-based stage interaction to improve accuracy over existing deep unfolding approaches.

Contribution

The paper proposes a pixel adaptive deep unfolding transformer with a spectral transformer and FFT-based stage interaction for enhanced hyperspectral image reconstruction.

Findings

Outperforms state-of-the-art methods on simulated data

Effective in real scene reconstructions

Demonstrates superior spectral and spatial recovery

Abstract

Hyperspectral Image (HSI) reconstruction has made gratifying progress with the deep unfolding framework by formulating the problem into a data module and a prior module. Nevertheless, existing methods still face the problem of insufficient matching with HSI data. The issues lie in three aspects: 1) fixed gradient descent step in the data module while the degradation of HSI is agnostic in the pixel-level. 2) inadequate prior module for 3D HSI cube. 3) stage interaction ignoring the differences in features at different stages. To address these issues, in this work, we propose a Pixel Adaptive Deep Unfolding Transformer (PADUT) for HSI reconstruction. In the data module, a pixel adaptive descent step is employed to focus on pixel-level agnostic degradation. In the prior module, we introduce the Non-local Spectral Transformer (NST) to emphasize the 3D characteristics of HSI for recovering. Moreover, inspired by the diverse expression of features in different stages and depths, the stage interaction is improved by the Fast Fourier Transform (FFT). Experimental results on both simulated and real scenes exhibit the superior performance of our method compared to state-of-the-art HSI reconstruction methods. The code is released at: https://github.com/MyuLi/PADUT.