RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging

TL;DR

RDFNet introduces a regional dynamic deep network for spectral image reconstruction, utilizing region-specific transformations and pixel-wise soft-thresholding to improve accuracy over existing methods.

Contribution

The paper proposes a novel regional dynamic FISTA-based network that adaptively adjusts transformations and soft-thresholding for different image regions, enhancing spectral reconstruction performance.

Findings

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

Effective in real-world spectral snapshot compressive imaging.

Demonstrates robustness across various datasets.

Abstract

Deep convolutional neural networks have recently shown promising results in compressive spectral reconstruction. Previous methods, however, usually adopt a single mapping function for sparse representation. Considering that different regions have distinct characteristics, it is desirable to apply various mapping functions to adjust different regions' transformations dynamically. With this in mind, we first introduce a regional dynamic way of using Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) to exploit regional characteristics and derive dynamic sparse representations. Then, we propose to unfold the process into a hierarchical dynamic deep network, dubbed RDFNet. The network comprises multiple regional dynamic blocks and corresponding pixel-wise adaptive soft-thresholding modules, respectively in charge of region-based dynamic mapping and pixel-wise soft-thresholding selection. The regional dynamic block guides the network to adjust the transformation domain for different regions. Equipped with the adaptive soft-thresholding, our proposed regional dynamic architecture can also learn appropriate shrinkage scale in a pixel-wise manner. Extensive experiments on both simulated and real data demonstrate that our method outperforms prior state-of-the-arts.