EUVIMEDEUVIMED entdecken
Crossref

Blur-Resistant Hyperspectral Image Super-Resolution via Dual-Degradation Fusion Model

Mai Xu, Yongxuan Dou, Xin Deng, Xin Zou, Zhenwei Shi

IEEE Transactions on Image Processing · 2026 · 35 · 8338-8353

DOI: 10.1109/tip.2026.3714832 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Mai Xu und 4 weiteren Autor:innen. Die Arbeit nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Nova Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The deep unfolding network represents a promising research avenue in fusion-based hyperspectral image super-resolution (HSI-SR). However, most current deep unfolding methodologies are anchored in idealized observation models, which overlook the degradation of the multispectral image (MSI), hindering their SR performance and practical applicability. To address this problem, this paper establishes a novel Dual-Degradation Fusion (D2-Fusion) model, which incorporates both HSI degradation and MSI blurring into the HSI-SR modeling process. Subsequently, we apply the second-order semismooth Newton algorithm to solve the optimization problem in D2-Fusion model. The solution steps are then mapped into an end-to-end trainable network, termed Blur-resistant Hyperspectral image Super-Resolution Network (BHSR-Net). To the best of our knowledge, the proposed network is the first successful attempt to consider MSI blurring artifacts in the HSI-SR task. It offers several distinct advantages: 1) The network structure maintains a strict mathematical correspondence with the optimization algorithm, ensuring each module retains strong physical interpretability; 2) The network exhibits superior SR performance and strong generalization ability on both standard and real-world scenarios across five datasets; 3) The network demonstrates excellent learning efficiency with a compact architecture, and its lightweight variant achieves comparable results with only 38K parameters. The code is available at https://github.com/Dou0405/BHSR-Net.

Förderung

  • National Natural Science Foundation of China
  • Beijing Nova Program

Zitieren

APA

Xu, M., Dou, Y., Deng, X., Zou, X., & Shi, Z. (2026). Blur-Resistant Hyperspectral Image Super-Resolution via Dual-Degradation Fusion Model. IEEE Transactions on Image Processing, 35, 8338-8353. https://doi.org/10.1109/tip.2026.3714832

Vancouver

Xu M, Dou Y, Deng X, Zou X, Shi Z. Blur-Resistant Hyperspectral Image Super-Resolution via Dual-Degradation Fusion Model. IEEE Transactions on Image Processing. 2026;35:8338-8353. doi:10.1109/tip.2026.3714832

BibTeX
@article{Xu2026,
  author = {Xu, Mai and Dou, Yongxuan and Deng, Xin and Zou, Xin and Shi, Zhenwei},
  title = {Blur-Resistant Hyperspectral Image Super-Resolution via Dual-Degradation Fusion Model},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {8338--8353},
  doi = {10.1109/tip.2026.3714832}
}
Kostenlos starten →