RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging
IEEE Transactions on Image Processing · 2024 · 33 · 2347-2360
DOI: 10.1109/tip.2024.3374093 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2024. Verfasst von Yin-Ping Zhao und 4 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 56 Literaturangaben. Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation, Natural Science Foundation of Shanxi Province.
Abstract (Originalsprache)
Deep unrolling-based snapshot compressive imaging (SCI) methods, which employ iterative formulas to construct interpretable iterative frameworks and embedded learnable modules, have achieved remarkable success in reconstructing 3-dimensional (3D) hyperspectral images (HSIs) from 2D measurement induced by coded aperture snapshot spectral imaging (CASSI). However, the existing deep unrolling-based methods are limited by the residuals associated with Taylor approximations and the poor representation ability of single hand-craft priors. To address these issues, we propose a novel HSI construction method named residual completion unrolling with mixed priors (RCUMP). RCUMP exploits a residual completion branch to solve the residual problem and incorporates mixed priors composed of a novel deep sparse prior and mask prior to enhance the representation ability. Our proposed CNN-based model can significantly reduce memory cost, which is an obvious improvement over previous CNN methods, and achieves better performance compared with the state-of-the-art transformer and RNN methods. In this work, our method is compared with the 9 most recent baselines on 10 scenes. The results show that our method consistently outperforms all the other methods while decreasing memory consumption by up to 80%.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Natural Science Foundation of Shanxi Province
- Guangdong Natural Science Foundation
- Shenzhen Science and Technology Program
Zitieren
APA
Zhao, Y. P., Zhang, J., Chen, Y., Wang, Z., & Li, X. (2024). RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging. IEEE Transactions on Image Processing, 33, 2347-2360. https://doi.org/10.1109/tip.2024.3374093
Vancouver
Zhao YP, Zhang J, Chen Y, Wang Z, Li X. RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging. IEEE Transactions on Image Processing. 2024;33:2347-2360. doi:10.1109/tip.2024.3374093
BibTeX
@article{Zhao2024,
author = {Zhao, Yin-Ping and Zhang, Jiancheng and Chen, Yongyong and Wang, Zhen and Li, Xuelong},
title = {RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging},
journal = {IEEE Transactions on Image Processing},
year = {2024},
volume = {33},
pages = {2347--2360},
doi = {10.1109/tip.2024.3374093}
}
EUVIMED