Constructive Solid Geometry on Neural Signed Distance Fields

10Citations
Citations of this article
17Readers
Mendeley users who have this article in their library.

Abstract

Signed Distance Fields (SDFs) parameterized by neural networks have recently gained popularity as a fundamental geometric representation. However, editing the shape encoded by a neural SDF remains an open challenge. A tempting approach is to leverage common geometric operators (e.g., boolean operations), but such edits often lead to incorrect non-SDF outputs (which we call Pseudo-SDFs), preventing them from being used for downstream tasks. In this paper, we characterize the space of Pseudo-SDFs, which are eikonal yet not true distance functions, and derive the closest point loss, a novel regularizer that encourages the output to be an exact SDF. We demonstrate the applicability of our regularization to many operations in which traditional methods cause a Pseudo-SDF to arise, such as CSG and swept volumes, and produce a true (neural) SDF for the result of these operations.

Cited by Powered by Scopus

Get full text

Ray Tracing Harmonic Functions

2Citations
10Readers
Get full text

A Unified Differentiable Boolean Operator with Fuzzy Logic

2Citations
5Readers
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Marschner, Z., Sellán, S., Liu, H. T. D., & Jacobson, A. (2023). Constructive Solid Geometry on Neural Signed Distance Fields. In Proceedings - SIGGRAPH Asia 2023 Conference Papers, SA 2023. Association for Computing Machinery, Inc. https://doi.org/10.1145/3610548.3618170

Readers' Seniority

Tooltip

Researcher 4

44%

Professor / Associate Prof. 3

33%

PhD / Post grad / Masters / Doc 2

22%

Readers' Discipline

Tooltip

Computer Science 9

100%

Save time finding and organizing research with Mendeley

Sign up for free