<metaname="twitter:title"content="Instant Neural Graphics Primitives with a Multiresolution Hash Encoding">
<metaname="twitter:description"content="A new paper from NVIDIA Research which presents a method for instant training & rendering of high-quality neural graphics primitives.">
<metaname="twitter:title"content="Instant Neural Graphics Primitives with a Multiresolution Hash Encoding">
<metaname="twitter:description"content="A new paper from NVIDIA Research which presents a method for instant training & rendering of high-quality neural graphics primitives.">
We demonstrate near-instant training of neural graphics primitives on a single GPU for multiple tasks. In <b>gigapixel image</b> we represent an image by a neural network. <b>SDF</b> learns a signed distance function in 3D space whose zero level-set represents a 2D surface.
<b>NeRF</b><ahref="https://research.nvidia.com/publication/2021-06_Real-time-Neural-Radiance">[Mildenhall et al. 2020]</a> uses 2D images and their camera poses to reconstruct a volumetric radiance-and-density field that is visualized using ray marching.
<b>NeRF</b><ahref="https://www.matthewtancik.com/nerf">[Mildenhall et al. 2020]</a> uses 2D images and their camera poses to reconstruct a volumetric radiance-and-density field that is visualized using ray marching.
Lastly, <b>neural volume</b> learns a denoised radiance and density field directly from a volumetric path tracer.
In all tasks, our encoding and its efficient implementation provide clear benefits: instant training, high quality, and simplicity. Our encoding is task-agnostic: we use the same implementation and hyperparameters across all tasks and only vary the hash table size which trades off quality and performance.
</p>
</figure>
</section>
<sectionid="news">
<h2>News</h2>
<hr>
...
...
@@ -334,7 +325,7 @@ figure {
</video>
</figure>
<pclass="caption_justify">
Real-time training progress on the image task where the neural network learns the mapping from 2D coordinates to RGB colors of a high-resolution image. Note that in this video, the network is trained from scratch - but converges so quickly you may miss it if you blink!<br/>
Real-time training progress on the image task where the neural network learns the mapping from 2D coordinates to RGB colors of a high-resolution image. Note that in this video, the network is trained from scratch—but converges so quickly you may miss it if you blink!<br/>