EUVIMEDEUVIMED entdecken
Crossref

Sampling Theory for Super-resolution with Implicit Neural Representations

Mahrokh Najaf, Gregory Ongie

SIAM Journal on Imaging Sciences · 30.06.2026 · 19 (2) · 1037-1076

DOI: 10.1137/25m1768175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Imaging Sciences, online erschienen am 11.05.2026. Verfasst von Mahrokh Najaf und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Division of Computing and Communication Foundations.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Implicit neural representations (INRs) have emerged as a powerful tool for solving inverse problems in computer vision and computational imaging. INRs represent images as continuous domain functions realized by a neural network taking spatial coordinates as inputs. However, unlike traditional pixel representations, little is known about the sample complexity of estimating images using INRs in the context of linear inverse problems. Towards this end, we study the sampling requirements for recovery of a continuous-domain image from its low-pass Fourier samples by fitting a single hidden-layer INR with ReLU activation and a Fourier features layer using a generalized form of weight decay regularization. Our key insight is to relate minimizers of this nonconvex parameter space optimization problem to minimizers of a convex penalty defined over an infinite-dimensional space of measures. We identify a sufficient number of Fourier samples for which an image realized by an INR is exactly recoverable by solving the INR training problem. To validate our theory, we empirically assess the probability of achieving exact recovery of images realized by low-width single hidden-layer INRs and illustrate the performance of INRs on super-resolution recovery of continuous domain phantom images.

Förderung

  • Division of Computing and Communication Foundations

Zitieren

APA

Najaf, M., & Ongie, G. (2026). Sampling Theory for Super-resolution with Implicit Neural Representations. SIAM Journal on Imaging Sciences, 19(2), 1037-1076. https://doi.org/10.1137/25m1768175

Vancouver

Najaf M, Ongie G. Sampling Theory for Super-resolution with Implicit Neural Representations. SIAM Journal on Imaging Sciences. 2026;19(2):1037-1076. doi:10.1137/25m1768175

BibTeX
@article{Najaf2026,
  author = {Najaf, Mahrokh and Ongie, Gregory},
  title = {Sampling Theory for Super-resolution with Implicit Neural Representations},
  journal = {SIAM Journal on Imaging Sciences},
  year = {2026},
  volume = {19},
  number = {2},
  pages = {1037--1076},
  doi = {10.1137/25m1768175}
}
Kostenlos starten →