Electrical engineering

Physics

Graphics

Volume rendering

3D computer graphics

Operating system

High fidelity

Optics

Computer graphics (images)

Software rendering

Engineering

Pixel

Artificial intelligence

Fidelity

Rendering (computer graphics)

Radiance

Extensibility

Computer science

Deep neural networks

Computer vision

Artificial neural network

Telecommunications

Alternate frame rendering

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.

FastNeRF: High-Fidelity Neural Rendering at 200FPS