# Instant neural graphics primitives with a multiresolution hash encoding

“Instant neural graphics primitives with a multiresolution hash encoding” (2022), by Thomas Müller et al. Computer Science research paper. Original abstract below, unchanged. A free PDF is available.

- Authors: Thomas Müller, Alex Evans, Christoph Schied, Alexander Keller
- Published: July 1, 2022
- Field: Computer Science
- DOI: https://doi.org/10.1145/3528223.3530127
- Free PDF: https://arxiv.org/pdf/2201.05989

## Abstract

Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of 1920×1080.

Canonical page: https://nerdi.pages.dev/paper/W4221151978
Read three real papers a day in Nerdi (iPhone): https://apps.apple.com/app/apple-store/id6813826387?pt=128757794&ct=web-paper&mt=8