Neural BRDF Importance Sampling by Reparameterization

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Liwen, Bi, Sai, Xu, Zexiang, Tan, Hao, Zhang, Kai, Luan, Fujun, Lu, Haolin, Ramamoorthi, Ravi
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912374599974912
author Wu, Liwen
Bi, Sai
Xu, Zexiang
Tan, Hao
Zhang, Kai
Luan, Fujun
Lu, Haolin
Ramamoorthi, Ravi
author_facet Wu, Liwen
Bi, Sai
Xu, Zexiang
Tan, Hao
Zhang, Kai
Luan, Fujun
Lu, Haolin
Ramamoorthi, Ravi
contents Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples. The reparameterization-based formulation transfers the distribution learning task to a problem of identifying BRDF integral substitutions. In contrast to previous methods that rely on invertible networks and multi-step inference to reconstruct BRDF distributions, our model removes these constraints, which offers greater flexibility and efficiency. Our variance and performance analysis demonstrates that our reparameterization method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2505_08998
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural BRDF Importance Sampling by Reparameterization
Wu, Liwen
Bi, Sai
Xu, Zexiang
Tan, Hao
Zhang, Kai
Luan, Fujun
Lu, Haolin
Ramamoorthi, Ravi
Graphics
Computer Vision and Pattern Recognition
Neural bidirectional reflectance distribution functions (BRDFs) have emerged as popular material representations for enhancing realism in physically-based rendering. Yet their importance sampling remains a significant challenge. In this paper, we introduce a reparameterization-based formulation of neural BRDF importance sampling that seamlessly integrates into the standard rendering pipeline with precise generation of BRDF samples. The reparameterization-based formulation transfers the distribution learning task to a problem of identifying BRDF integral substitutions. In contrast to previous methods that rely on invertible networks and multi-step inference to reconstruct BRDF distributions, our model removes these constraints, which offers greater flexibility and efficiency. Our variance and performance analysis demonstrates that our reparameterization method achieves the best variance reduction in neural BRDF renderings while maintaining high inference speeds compared to existing baselines.
title Neural BRDF Importance Sampling by Reparameterization
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.08998