Analyzing the Internals of Neural Radiance Fields

arXiv:2306.00696v2 Announce Type: replace
Abstract: Modern Neural Radiance Fields (NeRFs) learn a mapping from position to volumetric density leveraging proposal network samplers. In contrast to the coarse-to-fine sampling approach with two NeRFs, this offers significant potential for acceleration using lower network capacity. Given that NeRFs utilize most of their network capacity to estimate radiance, they could store valuable density information in their parameters or their deep features. To investigate this proposition, we take one step back and analyze large, trained …

abstract arxiv capacity contrast cs.cv cs.gr fields learn mapping modern network neural radiance fields sampling type