HEDU-Net: Improving Spectral Snapshot Compressive Imaging With Explicable Degradation Compensation
- 31 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 203-215
Abstract
With the widespread adoption of utilizing coded aperture snapshot spectral imaging (CASSI) to acquire hyperspectral images (HSIs), reconstruction algorithms become increasingly important as one of the most critical parts of CASSI. By formulating the iterative optimization problem as a multistage end-to-end neural network, the deep unfolding framework has made gratifying progress in improving the reconstruction reliability and fidelity. Nevertheless, there still exist three knotty issues limiting the performance of current reconstruction algorithms: 1) predetermined sensing matrix ignoring the gap between real and ideal degradation procedure. 2) ill-structured feature extraction and fusion network making it difficult to effectively recover the spatial texture and ensure spectral consistency. 3) inadequate stage interaction module, which hinders the transmission of useful information. To address these issues, in this paper, we propose a hyperspectral explicable degradation-compensatory unfolding neural network (HEDUNet), which attempts to dynamically compensate for the differences between ideal and real degradation procedures using a residual network under the deep unfolding strategy. Moreover, a spatial-spectral interaction transformer is designed via plugging the Swin transformer under the framework of the MixS2 transformer to independently excavate spatial or spectral features and fuse them thoroughly. Finally, to mitigate the information loss between adjacent stages, stage interaction is also enhanced by proposing a specific feature aggregation module based on the multi-scale attention mechanism. Experiments on both simulation and practical datasets show the state-of-the-art (SOTA) performance and wide application prospects of our method.Keywords
Funding Information
- National Natural Science Foundation of China (62403275)
This publication has 47 references indexed in Scilit:
- Enhanced deep unrolling networks for snapshot compressive hyperspectral imagingNeural Networks, 2024
- Learning Tensor Low-Rank Prior for Hyperspectral Image Reconstruction2021
- Effective Snapshot Compressive-spectral Imaging via Deep Denoising and Total Variation Priors2021
- End-to-End Low Cost Compressive Spectral Imaging with Spatial-Spectral Self-Attention2020
- DNU: Deep Non-Local Unrolling for Computational Spectral Imaging2020
- Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior2019
- ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements2016
- Exploiting Spectral-Spatial Correlation for Coded Hyperspectral Image Restoration2016
- A deep learning approach to structured signal recovery2015
- Detection of preinvasive cancer cellsNature, 2000