Guardado en:
Detalles Bibliográficos
Autores principales: Figueiredo, Pedro, He, Qihao, Bako, Steve, Kalantari, Nima Khademi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.11729
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912380894576640
author Figueiredo, Pedro
He, Qihao
Bako, Steve
Kalantari, Nima Khademi
author_facet Figueiredo, Pedro
He, Qihao
Bako, Steve
Kalantari, Nima Khademi
contents We propose a neural approach for estimating spatially varying light selection distributions to improve importance sampling in Monte Carlo rendering, particularly for complex scenes with many light sources. Our method uses a neural network to predict the light selection distribution at each shading point based on local information, trained by minimizing the KL-divergence between the learned and target distributions in an online manner. To efficiently manage hundreds or thousands of lights, we integrate our neural approach with light hierarchy techniques, where the network predicts cluster-level distributions and existing methods sample lights within clusters. Additionally, we introduce a residual learning strategy that leverages initial distributions from existing techniques, accelerating convergence during training. Our method achieves superior performance across diverse and challenging scenes.
format Preprint
id arxiv_https___arxiv_org_abs_2505_11729
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Importance Sampling of Many Lights
Figueiredo, Pedro
He, Qihao
Bako, Steve
Kalantari, Nima Khademi
Graphics
Machine Learning
We propose a neural approach for estimating spatially varying light selection distributions to improve importance sampling in Monte Carlo rendering, particularly for complex scenes with many light sources. Our method uses a neural network to predict the light selection distribution at each shading point based on local information, trained by minimizing the KL-divergence between the learned and target distributions in an online manner. To efficiently manage hundreds or thousands of lights, we integrate our neural approach with light hierarchy techniques, where the network predicts cluster-level distributions and existing methods sample lights within clusters. Additionally, we introduce a residual learning strategy that leverages initial distributions from existing techniques, accelerating convergence during training. Our method achieves superior performance across diverse and challenging scenes.
title Neural Importance Sampling of Many Lights
topic Graphics
Machine Learning
url https://arxiv.org/abs/2505.11729