Geometric implicit neural representations for signed distance functions
Abstract
\textit{Implicit neural representations} (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating \textit{signed distance functions} (SDFs) for surface scenes, using either oriented point clouds or a set of posed images. We refer to neural SDFs that incorporate differential geometry tools, such as normals and curvatures, in their loss functions as \textit{geometric} INRs. The key idea behind this 3D reconstruction approach is to include additional \textit{regularization} terms in the loss function, ensuring that the INR satisfies certain global properties that the function should hold -- such as having unit gradient in the case of SDFs. We explore key methodological components, including the definition of INR, the construction of geometric loss functions, and sampling schemes from a differential geometry perspective. Our review highlights the significant advancements enabled by geometric INRs in surface reconstruction from oriented point clouds and posed images.
Cite
@article{arxiv.2511.07206,
title = {Geometric implicit neural representations for signed distance functions},
author = {Luiz Schirmer and Tiago Novello and Vinícius da Silva and Guilherme Schardong and Daniel Perazzo and Hélio Lopes and Nuno Gonçalves and Luiz Velho},
journal= {arXiv preprint arXiv:2511.07206},
year = {2025}
}