Saved in:
Bibliographic Details
Main Authors: Bokšanský, Jakub, Meister, Daniel
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.05930
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911129025904640
author Bokšanský, Jakub
Meister, Daniel
author_facet Bokšanský, Jakub
Meister, Daniel
contents Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference on modern GPUs in real-time frame rates. The cache can be seamlessly integrated into existing rendering frameworks and can be used in combination with other real-time techniques such as spatiotemporal reservoir sampling (ReSTIR).
format Preprint
id arxiv_https___arxiv_org_abs_2506_05930
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Visibility Cache for Real-Time Light Sampling
Bokšanský, Jakub
Meister, Daniel
Graphics
Direct illumination with many lights is an inherent component of physically-based rendering, remaining challenging, especially in real-time scenarios. We propose an online-trained neural cache that stores visibility between lights and 3D positions. We feed light visibility to weighted reservoir sampling (WRS) to sample a light source. The cache is implemented as a fully-fused multilayer perceptron (MLP) with multi-resolution hash-grid encoding, enabling online training and efficient inference on modern GPUs in real-time frame rates. The cache can be seamlessly integrated into existing rendering frameworks and can be used in combination with other real-time techniques such as spatiotemporal reservoir sampling (ReSTIR).
title Neural Visibility Cache for Real-Time Light Sampling
topic Graphics
url https://arxiv.org/abs/2506.05930