CVGRJul 13, 2021

3D Parametric Wireframe Extraction Based on Distance Fields

arXiv:2107.06165v212 citations
AI Analysis

This work addresses 3D modeling and reconstruction for applications like CAD and computer graphics, but it appears incremental as it builds on existing wireframe extraction techniques.

The paper tackles the problem of extracting parametric wireframes from point clouds by processing a distance field to detect features and fit spline curves, resulting in superior quality compared to a deep learning-based method on 50 complex 3D shapes.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes