Litcius/Paper detail

Constructive Solid Geometry on Neural Signed Distance Fields

Zoë Marschner, Silvia Sellán, Hsueh‐Ti Derek Liu, Alec Jacobson

202324 citationsDOIOpen Access PDF

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.

Topics & Concepts

Signed distance functionComputer scienceParameterized complexityArtificial neural networkLeverage (statistics)Distance measuresAlgorithmRepresentation (politics)Artificial intelligenceMathematicsTheoretical computer scienceLawPoliticsPolitical scienceAdvanced Numerical Analysis Techniques3D Shape Modeling and AnalysisComputer Graphics and Visualization Techniques
Constructive Solid Geometry on Neural Signed Distance Fields | Litcius