NeuralPVS: Learned Estimation of Potentially Visible Sets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xiangyu, Köhler, Thomas, Qiu, Jun Lin, Mori, Shohei, Steinberger, Markus, Schmalstieg, Dieter
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908565750415360
author Wang, Xiangyu
Köhler, Thomas
Qiu, Jun Lin
Mori, Shohei
Steinberger, Markus
Schmalstieg, Dieter
author_facet Wang, Xiangyu
Köhler, Thomas
Qiu, Jun Lin
Mori, Shohei
Steinberger, Markus
Schmalstieg, Dieter
contents Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step on a static scene. We present NeuralPVS, the first deep-learning approach for visibility computation that efficiently determines from-region visibility in a large scene, running at approximately 100 Hz processing with less than $1\%$ missing geometry. This approach is possible by using a neural network operating on a voxelized representation of the scene. The network's performance is achieved by combining sparse convolution with a 3D volume-preserving interleaving for data compression. Moreover, we introduce a novel repulsive visibility loss that can effectively guide the network to converge to the correct data distribution. This loss provides enhanced robustness and generalization to unseen scenes. Our results demonstrate that NeuralPVS outperforms existing methods in terms of both accuracy and efficiency, making it a promising solution for real-time visibility computation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24677
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeuralPVS: Learned Estimation of Potentially Visible Sets
Wang, Xiangyu
Köhler, Thomas
Qiu, Jun Lin
Mori, Shohei
Steinberger, Markus
Schmalstieg, Dieter
Graphics
I.3.7
Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step on a static scene. We present NeuralPVS, the first deep-learning approach for visibility computation that efficiently determines from-region visibility in a large scene, running at approximately 100 Hz processing with less than $1\%$ missing geometry. This approach is possible by using a neural network operating on a voxelized representation of the scene. The network's performance is achieved by combining sparse convolution with a 3D volume-preserving interleaving for data compression. Moreover, we introduce a novel repulsive visibility loss that can effectively guide the network to converge to the correct data distribution. This loss provides enhanced robustness and generalization to unseen scenes. Our results demonstrate that NeuralPVS outperforms existing methods in terms of both accuracy and efficiency, making it a promising solution for real-time visibility computation.
title NeuralPVS: Learned Estimation of Potentially Visible Sets
topic Graphics
I.3.7
url https://arxiv.org/abs/2509.24677