GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yong, Silong, Xie, Yaqi, Stepputtis, Simon, Sycara, Katia
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916455748993024
author Yong, Silong
Xie, Yaqi
Stepputtis, Simon
Sycara, Katia
author_facet Yong, Silong
Xie, Yaqi
Stepputtis, Simon
Sycara, Katia
contents Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, We propose GL-NeRF, a new perspective of computing volume rendering with the Gauss-Laguerre quadrature. GL-NeRF significantly reduces the number of MLP calls needed for volume rendering, introducing no additional data structures or neural networks. The simple formulation makes adopting GL-NeRF in any NeRF model possible. In the paper, we first justify the use of the Gauss-Laguerre quadrature and then demonstrate this plug-and-play attribute by implementing it in two different NeRF models. We show that with a minimal drop in performance, GL-NeRF can significantly reduce the number of MLP calls, showing the potential to speed up any NeRF model.
format Preprint
id arxiv_https___arxiv_org_abs_2410_19831
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
Yong, Silong
Xie, Yaqi
Stepputtis, Simon
Sycara, Katia
Computer Vision and Pattern Recognition
Graphics
Volume rendering in neural radiance fields is inherently time-consuming due to the large number of MLP calls on the points sampled per ray. Previous works would address this issue by introducing new neural networks or data structures. In this work, We propose GL-NeRF, a new perspective of computing volume rendering with the Gauss-Laguerre quadrature. GL-NeRF significantly reduces the number of MLP calls needed for volume rendering, introducing no additional data structures or neural networks. The simple formulation makes adopting GL-NeRF in any NeRF model possible. In the paper, we first justify the use of the Gauss-Laguerre quadrature and then demonstrate this plug-and-play attribute by implementing it in two different NeRF models. We show that with a minimal drop in performance, GL-NeRF can significantly reduce the number of MLP calls, showing the potential to speed up any NeRF model.
title GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2410.19831