Non-uniform Point Cloud Upsampling via Local Manifold Distribution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fang, Yaohui, Wang, Xingce
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913796272947200
author Fang, Yaohui
Wang, Xingce
author_facet Fang, Yaohui
Wang, Xingce
contents Existing learning-based point cloud upsampling methods often overlook the intrinsic data distribution charac?teristics of point clouds, leading to suboptimal results when handling sparse and non-uniform point clouds. We propose a novel approach to point cloud upsampling by imposing constraints from the perspective of manifold distributions. Leveraging the strong fitting capability of Gaussian functions, our method employs a network to iteratively optimize Gaussian components and their weights, accurately representing local manifolds. By utilizing the probabilistic distribution properties of Gaussian functions, we construct a unified statistical manifold to impose distribution constraints on the point cloud. Experimental results on multiple datasets demonstrate that our method generates higher-quality and more uniformly distributed dense point clouds when processing sparse and non-uniform inputs, outperforming state-of-the-art point cloud upsampling techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11701
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Non-uniform Point Cloud Upsampling via Local Manifold Distribution
Fang, Yaohui
Wang, Xingce
Computer Vision and Pattern Recognition
Differential Geometry
Existing learning-based point cloud upsampling methods often overlook the intrinsic data distribution charac?teristics of point clouds, leading to suboptimal results when handling sparse and non-uniform point clouds. We propose a novel approach to point cloud upsampling by imposing constraints from the perspective of manifold distributions. Leveraging the strong fitting capability of Gaussian functions, our method employs a network to iteratively optimize Gaussian components and their weights, accurately representing local manifolds. By utilizing the probabilistic distribution properties of Gaussian functions, we construct a unified statistical manifold to impose distribution constraints on the point cloud. Experimental results on multiple datasets demonstrate that our method generates higher-quality and more uniformly distributed dense point clouds when processing sparse and non-uniform inputs, outperforming state-of-the-art point cloud upsampling techniques.
title Non-uniform Point Cloud Upsampling via Local Manifold Distribution
topic Computer Vision and Pattern Recognition
Differential Geometry
url https://arxiv.org/abs/2504.11701