Implicit Conversion of Manifold B-Rep Solids by Neural Halfspace Representation

TL;DR

This paper introduces NH-Rep, a neural implicit representation that converts manifold B-Rep CAD models into accurate, feature-preserving implicit forms using a Boolean tree structure and neural network optimization.

Contribution

The paper presents a novel neural halfspace representation (NH-Rep) for converting manifold B-Rep solids into implicit forms, preserving sharp features and improving reconstruction quality.

Findings

High-quality conversion on 10,000 CAD models with curved patches.

Outperforms existing implicit conversion algorithms in surface reconstruction.

Robustly handles various complex surface geometries.

Abstract

We present a novel implicit representation -- neural halfspace representation (NH-Rep), to convert manifold B-Rep solids to implicit representations. NH-Rep is a Boolean tree built on a set of implicit functions represented by the neural network, and the composite Boolean function is capable of representing solid geometry while preserving sharp features. We propose an efficient algorithm to extract the Boolean tree from a manifold B-Rep solid and devise a neural network-based optimization approach to compute the implicit functions. We demonstrate the high quality offered by our conversion algorithm on ten thousand manifold B-Rep CAD models that contain various curved patches including NURBS, and the superiority of our learning approach over other representative implicit conversion algorithms in terms of surface reconstruction, sharp feature preservation, signed distance field approximation, and robustness to various surface geometry, as well as a set of applications supported by NH-Rep.