GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
This addresses the computational bottleneck in NeRF models for 3D scene reconstruction, offering a plug-and-play acceleration method, though it is incremental as it builds on existing NeRF frameworks.
The paper tackles the slow volume rendering in neural radiance fields by proposing GL-NeRF, which uses Gauss-Laguerre quadrature to reduce MLP calls, achieving a minimal performance drop while significantly accelerating rendering.
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.