Neural Visibility of Point Sets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Jun-Hao, Tian, Yi-Yang, Chen, Baoquan, Wang, Peng-Shuai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908563862978560
author Wang, Jun-Hao
Tian, Yi-Yang
Chen, Baoquan
Wang, Peng-Shuai
author_facet Wang, Jun-Hao
Tian, Yi-Yang
Chen, Baoquan
Wang, Peng-Shuai
contents Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditional methods, such as Hidden Point Removal (HPR), face limitations in computational efficiency, robustness to noise, and handling concave regions or low-density point clouds. In this paper, we propose a novel approach to visibility determination in point clouds by formulating it as a binary classification task. The core of our network consists of a 3D U-Net that extracts view-independent point-wise features and a shared multi-layer perceptron (MLP) that predicts point visibility using the extracted features and view direction as inputs. The network is trained end-to-end with ground-truth visibility labels generated from rendered 3D models. Our method significantly outperforms HPR in both accuracy and computational efficiency, achieving up to 126 times speedup on large point clouds. Additionally, our network demonstrates robustness to noise and varying point cloud densities and generalizes well to unseen shapes. We validate the effectiveness of our approach through extensive experiments on the ShapeNet, ABC Dataset and real-world datasets, showing substantial improvements in visibility accuracy. We also demonstrate the versatility of our method in various applications, including point cloud visualization, surface reconstruction, normal estimation, shadow rendering, and viewpoint optimization. Our code and models are available at https://github.com/octree-nn/neural-visibility.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Visibility of Point Sets
Wang, Jun-Hao
Tian, Yi-Yang
Chen, Baoquan
Wang, Peng-Shuai
Graphics
Computer Vision and Pattern Recognition
Point clouds are widely used representations of 3D data, but determining the visibility of points from a given viewpoint remains a challenging problem due to their sparse nature and lack of explicit connectivity. Traditional methods, such as Hidden Point Removal (HPR), face limitations in computational efficiency, robustness to noise, and handling concave regions or low-density point clouds. In this paper, we propose a novel approach to visibility determination in point clouds by formulating it as a binary classification task. The core of our network consists of a 3D U-Net that extracts view-independent point-wise features and a shared multi-layer perceptron (MLP) that predicts point visibility using the extracted features and view direction as inputs. The network is trained end-to-end with ground-truth visibility labels generated from rendered 3D models. Our method significantly outperforms HPR in both accuracy and computational efficiency, achieving up to 126 times speedup on large point clouds. Additionally, our network demonstrates robustness to noise and varying point cloud densities and generalizes well to unseen shapes. We validate the effectiveness of our approach through extensive experiments on the ShapeNet, ABC Dataset and real-world datasets, showing substantial improvements in visibility accuracy. We also demonstrate the versatility of our method in various applications, including point cloud visualization, surface reconstruction, normal estimation, shadow rendering, and viewpoint optimization. Our code and models are available at https://github.com/octree-nn/neural-visibility.
title Neural Visibility of Point Sets
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.24150