paper-with-me

Papers

Geometric implicit neural representations for signed distance functions

2025-11-10 · Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho arxiv

\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.

📄 PDF Abstract BibTeX arXiv:2511.07206

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionPoint Clouds

Similar Papers 제목 키워드 기반

SAL: Sign Agnostic Learning of Shapes from Raw Data

2019-11-23 · CVPR 2020 6 · Matan Atzmon, Yaron Lipman

Recently, neural networks have been used as implicit representations for surface reconstruction, modelling, learning, and generation. So far, training neural networks to be implicit representations of surfaces required t…

Deep LearningSurface Reconstruction

SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces

2026-04-15 · Chuanxiang Yang, Junhui Hou, Yuan Liu, Siyu Ren 외 arxiv

Implicit neural representations are powerful for geometric modeling, but their practical use is often limited by the high computational cost of network evaluations. We observe that implicit representations require progre…

BayesSDF: Surface-Based Laplacian Uncertainty Estimation for 3D Geometry with Neural Signed Distance Fields

2025-07-08 · Rushil Desai arxiv

Accurate surface estimation is critical for downstream tasks in scientific simulation, and quantifying uncertainty in implicit neural 3D representations still remains a substantial challenge due to computational ineffici…

Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes

2025-09-25 · Christian Stippel, Felix Mujkanovic, Thomas Leimkühler, Pedro Hermosilla arxiv

Accurate surface geometry representation is crucial in 3D visual computing. Explicit representations, such as polygonal meshes, and implicit representations, like signed distance functions, each have distinct advantages,…

Implicit Filtering for Learning Neural Signed Distance Functions from 3D Point Clouds

2024-07-18 · Shengtao Li, Ge Gao, Yudong Liu, Ming Gu 외

Neural signed distance functions (SDFs) have shown powerful ability in fitting the shape geometry. However, inferring continuous signed distance fields from discrete unoriented point clouds still remains a challenge. The…

Surface Reconstruction