Using K-Means clustering to export a NeRF for faster rendering in CG applications while preserving view-dependent appearance
J.J.K. Groenendijk (TU Delft - Electrical Engineering, Mathematics and Computer Science)
E. Eisemann – Mentor (TU Delft - Computer Graphics and Visualisation)
P. Kellnhofer – Mentor (TU Delft - Computer Graphics and Visualisation)
M. Weinmann – Mentor (TU Delft - Computer Graphics and Visualisation)
J.C. Gemert – Graduation committee member (TU Delft - Pattern Recognition and Bioinformatics)
More Info
expand_more
The repository that contains the code used in the paper.
https://github.com/jurrejelle/nerf2meshOther than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
With the current state-of-the-art research, exporting a NeRF to a mesh has the side effect of having to evaluate a Multi Layer Perceptron at render-time, causing a significant decrease in performance. We have found a way to use K-Means clustering to pre-compute values for this MLP, storing them in multiple octahedron maps for the GPU to fetch when it's time to render the object. This improves render times by a factor of 3-4x.