Using K-Means clustering to export a NeRF for faster rendering in CG applications while preserving view-dependent appearance

Bachelor thesis (2023)

Authors

J.J.K. Groenendijk Electrical Engineering, Mathematics and Computer Science

Contributors

E. Eisemann Computer Graphics and Visualisation - EEMCS (mentor)
P. Kellnhofer Computer Graphics and Visualisation - EEMCS (mentor)
M. Weinmann Computer Graphics and Visualisation - EEMCS (mentor)
J.C. van Gemert Pattern Recognition and Bioinformatics - EEMCS (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright: © 2023 Jurre Groenendijk
More Info
expand_more

Published Date

05-07-2023

Language

English

Reuse Rights

Other 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.

Faculty

Electrical Engineering, Mathematics and Computer Science

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.

Files

Research_Project_Jurre_Groenen... (pdf)
(pdf | 0.154 Mb)
Unknown license