EUVIMEDEUVIMED entdecken
Crossref

NeurTV: Total Variation on the Neural Domain

Yisi Luo, Xile Zhao, Kai Ye, Deyu Meng

SIAM Journal on Imaging Sciences · 30.06.2025 · 18 (2) · 1101-1140

DOI: 10.1137/24m1664605 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Imaging Sciences, online erschienen am 28.04.2025. Verfasst von Yisi Luo und 3 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: Major Key Project of PCL, Sichuan Science and Technology Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, we have witnessed the success of total variation (TV) for many imaging applications. However, traditional TV is defined on the original pixel domain, which limits its potential. In this work, we suggest a new TV regularization defined on the neural domain. Concretely, the discrete data is implicitly and continuously represented by a deep neural network (DNN), and we use the derivatives of DNN outputs with respect to (w.r.t.) input coordinates to capture local correlations of data. As compared with classical TV on the original domain, the proposed TV on the neural domain (termed NeurTV) enjoys the following advantages. First, NeurTV is free of discretization error induced by the discrete difference operator. Second, NeurTV is not limited to meshgrid but is suitable for both meshgrid and non-meshgrid data. Third, NeurTV can more exactly capture local correlations across data for any direction and any order of derivatives attributed to the implicit and continuous nature of neural domain. We theoretically reinterpret NeurTV under the variational approximation framework, which allows us to build the connection between NeurTV and classical TV and inspires us to develop variants (e.g., space-variant NeurTV). Extensive numerical experiments with meshgrid data (e.g., color and hyperspectral images) and non-meshgrid data (e.g., point clouds and spatial transcriptomics) showcase the effectiveness of the proposed methods.

Förderung

  • Major Key Project of PCL
  • Sichuan Science and Technology Program
  • National Natural Science Foundation of China
  • National Key R_D Program of China

Zitieren

APA

Luo, Y., Zhao, X., Ye, K., & Meng, D. (2025). NeurTV: Total Variation on the Neural Domain. SIAM Journal on Imaging Sciences, 18(2), 1101-1140. https://doi.org/10.1137/24m1664605

Vancouver

Luo Y, Zhao X, Ye K, Meng D. NeurTV: Total Variation on the Neural Domain. SIAM Journal on Imaging Sciences. 2025;18(2):1101-1140. doi:10.1137/24m1664605

BibTeX
@article{Luo2025,
  author = {Luo, Yisi and Zhao, Xile and Ye, Kai and Meng, Deyu},
  title = {NeurTV: Total Variation on the Neural Domain},
  journal = {SIAM Journal on Imaging Sciences},
  year = {2025},
  volume = {18},
  number = {2},
  pages = {1101--1140},
  doi = {10.1137/24m1664605}
}
Kostenlos starten →