Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kong, Jiayi, Zong, Chen, Deng, Junkai, Chen, Xuhui, Hou, Fei, Xin, Shiqing, Hou, Junhui, Qian, Chen, He, Ying
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915554495823872
author Kong, Jiayi
Zong, Chen
Deng, Junkai
Chen, Xuhui
Hou, Fei
Xin, Shiqing
Hou, Junhui
Qian, Chen
He, Ying
author_facet Kong, Jiayi
Zong, Chen
Deng, Junkai
Chen, Xuhui
Hou, Fei
Xin, Shiqing
Hou, Junhui
Qian, Chen
He, Ying
contents Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orientable and non-orientable geometries, and non-manifold structures. While recent neural approaches have shown promise in learning UDFs, they often suffer from numerical instability, high computational cost, and limited controllability. We present a lightweight, network-free method, Voronoi-Assisted Diffusion (VAD), for computing UDFs directly from unoriented point clouds. Our approach begins by assigning bi-directional normals to input points, guided by two Voronoi-based geometric criteria encoded in an energy function for optimal alignment. The aligned normals are then diffused to form an approximate UDF gradient field, which is subsequently integrated to recover the final UDF. Experiments demonstrate that VAD robustly handles watertight and open surfaces, as well as complex non-manifold and non-orientable geometries, while remaining computationally efficient and stable.
format Preprint
id arxiv_https___arxiv_org_abs_2510_12524
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points
Kong, Jiayi
Zong, Chen
Deng, Junkai
Chen, Xuhui
Hou, Fei
Xin, Shiqing
Hou, Junhui
Qian, Chen
He, Ying
Computer Vision and Pattern Recognition
Unsigned Distance Fields (UDFs) provide a flexible representation for 3D shapes with arbitrary topology, including open and closed surfaces, orientable and non-orientable geometries, and non-manifold structures. While recent neural approaches have shown promise in learning UDFs, they often suffer from numerical instability, high computational cost, and limited controllability. We present a lightweight, network-free method, Voronoi-Assisted Diffusion (VAD), for computing UDFs directly from unoriented point clouds. Our approach begins by assigning bi-directional normals to input points, guided by two Voronoi-based geometric criteria encoded in an energy function for optimal alignment. The aligned normals are then diffused to form an approximate UDF gradient field, which is subsequently integrated to recover the final UDF. Experiments demonstrate that VAD robustly handles watertight and open surfaces, as well as complex non-manifold and non-orientable geometries, while remaining computationally efficient and stable.
title Voronoi-Assisted Diffusion for Computing Unsigned Distance Fields from Unoriented Points
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.12524