Depth Light Field Training (DeLFT)
NeRF as a rendering primitive
M.A. Toader (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
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.
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.