EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Neural Geometry Processing via Spherical Neural Surfaces

Romy Williamson, Niloy J. Mitra

Computer Graphics Forum · 2025-05 · 44 (2)

DOI: 10.1111/cgf.70021 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 15.04.2025. Verfasst von Romy Williamson und 1 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural surfaces (e.g., neural map encoding, deep implicit, and neural radiance fields) have recently gained popularity because of their generic structure (e.g., multi‐layer perceptron) and easy integration with modern learning‐based setups. Traditionally, we have a rich toolbox of geometry processing algorithms designed for polygonal meshes to analyze and operate on surface geometry. Without an analogous toolbox, neural representations are typically discretized and converted into a mesh, before applying any geometry processing algorithm. This is unsatisfactory and, as we demonstrate, unnecessary. In this work, we propose a spherical neural surface representation for genus‐0 surfaces and demonstrate how to compute core geometric operators directly on this representation. Namely, we estimate surface normals and first and second fundamental forms of the surface, as well as compute surface gradient, surface divergence and Laplace Beltrami operator on scalar/vector fields defined on the surface. Our representation is fully seamless, overcoming a key limitation of similar explicit representations such as Neural Surface Maps [MAKM21]. These operators, in turn, enable geometry processing directly on the neural representations without any unnecessary meshing. We demonstrate illustrative applications in (neural) spectral analysis, heat flow and mean curvature flow, and evaluate robustness to isometric shape variations. We propose theoretical formulations and validate their numerical estimates, against analytical estimates, mesh‐based baselines, and neural alternatives, where available. By systematically linking neural surface representations with classical geometry processing algorithms, we believe this work can become a key ingredient in enabling neural geometry processing. Code is available via the project webpage.

Förderung

  • Engineering and Physical Sciences Research Council

Zitieren

APA

Williamson, R., & Mitra, N. J. (2025). Neural Geometry Processing via Spherical Neural Surfaces. Computer Graphics Forum, 44(2). https://doi.org/10.1111/cgf.70021

Vancouver

Williamson R, Mitra NJ. Neural Geometry Processing via Spherical Neural Surfaces. Computer Graphics Forum. 2025;44(2). doi:10.1111/cgf.70021

BibTeX
@article{Williamson2025,
  author = {Williamson, Romy and Mitra, Niloy J.},
  title = {Neural Geometry Processing via Spherical Neural Surfaces},
  journal = {Computer Graphics Forum},
  year = {2025},
  volume = {44},
  number = {2},
  doi = {10.1111/cgf.70021}
}
Kostenlos starten →