EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A New Image Denoising Model Based on Low-Rank and Deep Image Prior

Liwen Feng, Yan Hao, Zirui Mao, Jiaojiao Xu, Jianlou Xu

Symmetry · 05.04.2026 · 18 (4) · 618

DOI: 10.3390/sym18040618 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 05.04.2026. Verfasst von Liwen Feng und 4 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Science and Technology Research Project of Henan Province of China, Henan University of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Low-rank recovery has emerged as a powerful methodology for the restoration of degraded images. Conventional low-rank recovery techniques, however, predominantly rely on nuclear norm or weighted nuclear norm minimization to separate sparse noise. A significant limitation of this approach is its dependence on full singular value decomposition, which imposes a substantial computational burden, thereby hindering its practical applicability. This paper presents a novel image denoising model integrating the weighted nuclear norm and deep image prior. The weighted nuclear norm is introduced to accurately characterize the global structural properties of images, ensuring the consistency of the overall image structure after denoising. Meanwhile, the deep image prior is employed to effectively capture local details, which helps avoid the blurring of textures and edges often caused by excessive noise removal. The complementary advantages of the two components enable the proposed model to achieve superior performance compared with existing denoising methods. To efficiently compute the proposed model, we design the bilinear factorization method and the alternating direction method of multipliers. Experiments show that the proposed method outperforms mainstream approaches in both restoration accuracy and computational efficiency, exhibiting rapid convergence and robust algorithm stability, thereby demonstrating excellent comprehensive performance.

Förderung

  • Key Science and Technology Research Project of Henan Province of China
  • Henan University of Science and Technology

Zitieren

APA

Feng, L., Hao, Y., Mao, Z., Xu, J., & Xu, J. (2026). A New Image Denoising Model Based on Low-Rank and Deep Image Prior. Symmetry, 18(4), 618. https://doi.org/10.3390/sym18040618

Vancouver

Feng L, Hao Y, Mao Z, Xu J, Xu J. A New Image Denoising Model Based on Low-Rank and Deep Image Prior. Symmetry. 2026;18(4):618. doi:10.3390/sym18040618

BibTeX
@article{Feng2026,
  author = {Feng, Liwen and Hao, Yan and Mao, Zirui and Xu, Jiaojiao and Xu, Jianlou},
  title = {A New Image Denoising Model Based on Low-Rank and Deep Image Prior},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {4},
  pages = {618},
  doi = {10.3390/sym18040618}
}
Kostenlos starten →