3D Parametric Wireframe Extraction Based on Distance Fields

TL;DR

This paper introduces a pipeline for extracting editable parametric wireframes from dense point clouds by leveraging distance fields, detecting features, and fitting spline curves, outperforming deep learning methods.

Contribution

It presents a novel approach combining distance fields and topological graph fitting for wireframe extraction, enabling high-quality, editable parametric models.

Findings

Outperforms deep learning-based methods in quality

Successfully applied to 50 complex 3D shapes

Produces editable spline-based wireframes

Abstract

We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.