Skip to content

Instant neural graphics primitives with a multiresolution hash encoding

Thomas Müller, Alex Evans, Christoph Schied, Alexander Keller

ACM Transactions on Graphics · 2022 · 4,917 citationsOpen access

No retraction on record in OpenAlex.Check Crossref now

Cite this paper

Müller, T., Evans, A., Schied, C., & Keller, A. (2022). Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics, 41(4), 1–15. https://doi.org/10.1145/3528223.3530127

In text: (Müller et al., 2022)

Ask a question about this research

One question, free, no account. Anchorcite finds the papers, checks each against Crossref and links every sentence of the answer to the passage it comes from.

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.

  1. GAN(Generative Adversarial Nets)2017
  2. Generative adversarial networks2020
  3. A survey on Image Data Augmentation for Deep Learning2019
  4. A Style-Based Generator Architecture for Generative Adversarial Networks2019
  5. Caffe2014

Metadata from OpenAlex (CC0). Citations are generated from the published record.