RDFNet: Regional Dynamic FISTA-Net for Spectral Snapshot Compressive Imaging
arXiv:2302.02519 · doi:10.1109/TCI.2023.3237175
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.
arXiv commentIEEE Transactions on Computational Imaging
References in corpus (8)
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- Rank Minimization for Snapshot Compressive Imaging
- Dynamic Filter Networks
- A survey on computational spectral reconstruction methods from RGB to hyperspectral imaging
- Compressed Sensing with Deep Image Prior and Learned Regularization
- GAP-net for Snapshot Compressive Imaging
- Compressive Spectral Image Reconstruction using Deep Prior and Low-Rank Tensor Representation
- Compressive dual-comb spectroscopy