Spectral Compressive Imaging Reconstruction Using Convolution and Contextual Transformer

TL;DR

This paper introduces a hybrid neural network module combining convolution and transformer techniques to significantly improve the quality and speed of spectral compressive imaging reconstruction.

Contribution

It proposes the CCoT block integrated into a deep unfolding framework, achieving superior reconstruction quality and efficiency over existing methods.

Findings

>2dB PSNR improvement on benchmark datasets

Faster reconstruction times than SOTA algorithms

Effective restoration of fine details in hyperspectral images

Abstract

Spectral compressive imaging (SCI) is able to encode the high-dimensional hyperspectral image to a 2D measurement, and then uses algorithms to reconstruct the spatio-spectral data-cube. At present, the main bottleneck of SCI is the reconstruction algorithm, and the state-of-the-art (SOTA) reconstruction methods generally face the problem of long reconstruction time and/or poor detail recovery. In this paper, we propose a novel hybrid network module, namely CCoT (Convolution and Contextual Transformer) block, which can acquire the inductive bias ability of convolution and the powerful modeling ability of transformer simultaneously,and is conducive to improving the quality of reconstruction to restore fine details. We integrate the proposed CCoT block into deep unfolding framework based on the generalized alternating projection algorithm, and further propose the GAP-CCoT network. Through the experiments of extensive synthetic and real data, our proposed model achieves higher reconstruction quality ($>$2dB in PSNR on simulated benchmark datasets) and shorter running time than existing SOTA algorithms by a large margin. The code and models are publicly available at https://github.com/ucaswangls/GAP-CCoT.