EUVIMEDEUVIMED entdecken
Crossref

DDIP: Mutual-Regularized Dual Deep Image Prior for Self-Supervised Compressive Spectral Imaging

Lizhu Liu, Yaonan Wang, Yurong Chen, Hui Zhang

IEEE Transactions on Circuits and Systems for Video Technology · 2026-02 · 36 (2) · 1558-1570

DOI: 10.1109/tcsvt.2025.3598407 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-02. Verfasst von Lizhu Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China, Major Research Plan of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, numerous hyperspectral image (HSI) reconstruction methods have been proposed to enhance the imaging quality of coded aperture snapshot spectral compressive imaging (CASSI) systems. Among these methods, self-supervised Deep Image Prior (DIP)-based approaches have gained attention for their ability to reconstruct three-dimensional (3D) HSIs without the need for external training data. However, DIP methods often suffer from overfitting to high-frequency noise during the optimization process, leading to artifacts and loss of fine details. To address these challenges, we propose a Mutual-Regularized Dual Deep Image Prior (DDIP) framework that employs implicit mutual regularization between two DIP networks. By encouraging mutual constraints, DDIP effectively mitigates high-frequency learning bias and suppresses noise amplification. Additionally, we employ a Half Quadratic Splitting (HQS) optimization strategy to ensure stable and efficient convergence, progressively integrating complementary information from the dual networks. We provide a comprehensive convergence analysis of the DDIP framework and establish theoretical conditions to guide the progressive fusion of the dual networks, ensuring robust and reliable reconstruction. Based on the insights from the convergence analysis, we introduce an Adaptive Deep Image Prior inner-loop strategy that dynamically adjusts the inner-loop updates, ensuring balanced learning of low- and high-frequency components. Moreover, a Residual Spectral-Spatial Feature Attention Network (SSFAN) is designed to enhance spectral-spatial feature extraction, further improving reconstruction accuracy. Extensive experiments on benchmark datasets demonstrate that DDIP achieves competitive HSI reconstruction quality compared to state-of-the-art unsupervised and self-supervised methods.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Major Research Plan of the National Natural Science Foundation of China
  • Hunan Leading Talent of Technological Innovation
  • Hunan Science Fund for Distinguished Young Scholars
  • Joint Open Foundation of State Key Laboratory of Robotics

Zitieren

APA

Liu, L., Wang, Y., Chen, Y., & Zhang, H. (2026). DDIP: Mutual-Regularized Dual Deep Image Prior for Self-Supervised Compressive Spectral Imaging. IEEE Transactions on Circuits and Systems for Video Technology, 36(2), 1558-1570. https://doi.org/10.1109/tcsvt.2025.3598407

Vancouver

Liu L, Wang Y, Chen Y, Zhang H. DDIP: Mutual-Regularized Dual Deep Image Prior for Self-Supervised Compressive Spectral Imaging. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(2):1558-1570. doi:10.1109/tcsvt.2025.3598407

BibTeX
@article{Liu2026,
  author = {Liu, Lizhu and Wang, Yaonan and Chen, Yurong and Zhang, Hui},
  title = {DDIP: Mutual-Regularized Dual Deep Image Prior for Self-Supervised Compressive Spectral Imaging},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {2},
  pages = {1558--1570},
  doi = {10.1109/tcsvt.2025.3598407}
}
Kostenlos starten →