Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kong, Jiayi, Zong, Chen, Luo, Jun, Xin, Shiqing, Hou, Fei, Jiang, Hanqing, Qian, Chen, He, Ying
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2410.17774
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912875785748480
author Kong, Jiayi
Zong, Chen
Luo, Jun
Xin, Shiqing
Hou, Fei
Jiang, Hanqing
Qian, Chen
He, Ying
author_facet Kong, Jiayi
Zong, Chen
Luo, Jun
Xin, Shiqing
Hou, Fei
Jiang, Hanqing
Qian, Chen
He, Ying
contents The medial axis, a lower-dimensional descriptor that captures the extrinsic structure of a shape, plays an important role in digital geometry processing. Despite its importance, computing the medial axis transform robustly from diverse inputs, especially point clouds with defects, remains a challenging problem. In this paper, we propose a new implicit method that deviates from traditional explicit medial axis computation. Our key technical insight is that the difference between the signed distance field (SDF) and the medial field (MF) of a solid shape relates to the unsigned distance field (UDF) of the shape's medial axis. This observation allows us to formulate medial axis extraction as an implicit reconstruction problem. By employing a modified double covering strategy, we recover the medial axis as the zero level-set of the UDF. Extensive experiments demonstrate that our method achieves higher accuracy and robustness in learning compact medial axis transforms from challenging meshes and point clouds, outperforming existing approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17774
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axes
Kong, Jiayi
Zong, Chen
Luo, Jun
Xin, Shiqing
Hou, Fei
Jiang, Hanqing
Qian, Chen
He, Ying
Computer Vision and Pattern Recognition
Graphics
The medial axis, a lower-dimensional descriptor that captures the extrinsic structure of a shape, plays an important role in digital geometry processing. Despite its importance, computing the medial axis transform robustly from diverse inputs, especially point clouds with defects, remains a challenging problem. In this paper, we propose a new implicit method that deviates from traditional explicit medial axis computation. Our key technical insight is that the difference between the signed distance field (SDF) and the medial field (MF) of a solid shape relates to the unsigned distance field (UDF) of the shape's medial axis. This observation allows us to formulate medial axis extraction as an implicit reconstruction problem. By employing a modified double covering strategy, we recover the medial axis as the zero level-set of the UDF. Extensive experiments demonstrate that our method achieves higher accuracy and robustness in learning compact medial axis transforms from challenging meshes and point clouds, outperforming existing approaches.
title Quasi-Medial Distance Field (Q-MDF): A Robust Method for Approximating and Discretizing Neural Medial Axes
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2410.17774