Coarse-Fine Spectral-Aware Deformable Convolution For Hyperspectral Image Reconstruction

TL;DR

This paper introduces CFSDCN, a novel deformable convolution network that effectively captures long-range dependencies and spectral similarities in hyperspectral image reconstruction, outperforming existing methods.

Contribution

The paper presents the first application of deformable convolutional networks to hyperspectral image reconstruction, incorporating spectral-aware modules for improved performance.

Findings

Significantly outperforms previous SOTA methods on multiple datasets.

Effectively captures long-range dependencies and spectral similarities.

Demonstrates robustness on both simulated and real HSI data.

Abstract

We study the inverse problem of Coded Aperture Snapshot Spectral Imaging (CASSI), which captures a spatial-spectral data cube using snapshot 2D measurements and uses algorithms to reconstruct 3D hyperspectral images (HSI). However, current methods based on Convolutional Neural Networks (CNNs) struggle to capture long-range dependencies and non-local similarities. The recently popular Transformer-based methods are poorly deployed on downstream tasks due to the high computational cost caused by self-attention. In this paper, we propose Coarse-Fine Spectral-Aware Deformable Convolution Network (CFSDCN), applying deformable convolutional networks (DCN) to this task for the first time. Considering the sparsity of HSI, we design a deformable convolution module that exploits its deformability to capture long-range dependencies and non-local similarities. In addition, we propose a new spectral information interaction module that considers both coarse-grained and fine-grained spectral similarities. Extensive experiments demonstrate that our CFSDCN significantly outperforms previous state-of-the-art (SOTA) methods on both simulated and real HSI datasets.