Score: 0

Geometric implicit neural representations for signed distance functions

Published: November 10, 2025 | arXiv ID: 2511.07206v1

By: Luiz Schirmer , Tiago Novello , Vinícius da Silva and more

Potential Business Impact:

Builds 3D shapes from pictures and points.

Business Areas:
Image Recognition Data and Analytics, Software

\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.

Country of Origin
🇧🇷 Brazil

Page Count
19 pages

Category
Computer Science:
CV and Pattern Recognition