EUVIMEDEUVIMED entdecken
Crossref

RCUMP: Residual Completion Unrolling With Mixed Priors for Snapshot Compressive Imaging

Yin-Ping Zhao, Jiancheng Zhang, Yongyong Chen, Zhen Wang, Xuelong Li

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.

AbstractBibliografische AngabenZitierenVerwandte Studien

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}
}
Kostenlos starten →