FastNeRF: High-Fidelity Neural Rendering at 200FPS release_wleeyu33h5cgbjlgfrvsqrrcyu

by Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, Julien Valentin

Released as a article .

2021  

Abstract

Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints. Rendering these images is very computationally demanding and recent improvements are still a long way from enabling interactive rates, even on high-end hardware. Motivated by scenarios on mobile and mixed reality devices, we propose FastNeRF, the first NeRF-based system capable of rendering high fidelity photorealistic images at 200Hz on a high-end consumer GPU. The core of our method is a graphics-inspired factorization that allows for (i) compactly caching a deep radiance map at each position in space, (ii) efficiently querying that map using ray directions to estimate the pixel values in the rendered image. Extensive experiments show that the proposed method is 3000 times faster than the original NeRF algorithm and at least an order of magnitude faster than existing work on accelerating NeRF, while maintaining visual quality and extensibility.
In text/plain format

Archived Files and Locations

application/pdf  1.0 MB
file_jfi2sghbsvdzbluq4npy77y2iu
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-03-18
Version   v1
Language   en ?
arXiv  2103.10380v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 2c78e558-ed39-47cd-a9e7-6d5697dde557
API URL: JSON