Depth Light Field Training (DeLFT)

NeRF as a rendering primitive

Bachelor thesis (2023)

Authors

M.A. Toader 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 Mihnea Toader
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

Neural radiance fields (NeRF) based solutions for novel view synthesis can achieve state of the art results. Recent work proposes models that take less time to render, need less training data or take up less space. However, few papers explore the use of NeRFs in classic rendering scenarios such as rasterization, which could contribute to wider adoption. Our paper tackles the issue of shadow generation and proposes a deep residual MLP network with fast evaluation times, that generates view-dependent shadow maps. The network distills the knowledge of an existing NeRF model and achieves the speedup through the use of neural light fields, by only doing one network forward per ray.

Files

Final_Paper_Mihnea_Toader.pdf
(pdf | 0.831 Mb)
Unknown license