2023/03/29 by Xiangyu Zhu, Zhu, Xiangyu, Du Dong +9 · 3 citations
Earth and Planetary Sciences · Engineering · Mathematics · #3D Shape Modeling and Analysis #3D Surveying and Cultural Heritage #Advanced Numerical Analysis Techniques #Algorithm #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #Enhanced Data Rates for GSM Evolution #FOS: Computer and information sciences #Geometry #Machine learning #Margin (machine learning) #Mathematics #Parametric model #Parametric statistics #Point (geometry) #Point cloud #Representation (politics)
paper · pdf · doi:10.48550/arxiv.2303.16465
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2023/03/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/01
Extracting parametric edge curves from point clouds is a fundamental problem in 3D vision and geometry processing. Existing approaches mainly rely on keypoint detection, a challenging procedure that tends to generate noisy output, making the subsequent edge extraction error-prone. To address this issue, we propose to directly detect structured edges to circumvent the limitations of the previous point-wise methods. We achieve this goal by presenting NerVE, a novel neural volumetric edge representation that can be easily learned through a volumetric learning framework. NerVE can be seamlessly converted to a versatile piece-wise linear (PWL) curve representation, enabling a unified strategy for learning all types of free-form curves. Furthermore, as NerVE encodes rich structural information, we show that edge extraction based on NerVE can be reduced to a simple graph search problem. After converting NerVE to the PWL representation, parametric curves can be obtained via off-the-shelf spline fitting algorithms. We evaluate our method on the challenging ABC dataset. We show that a simple network based on NerVE can already outperform the previous state-of-the-art methods by a great margin. Project page: https://dongdu3.github.io/projects/2023/NerVE/.