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>Neural radiance caching</b> (NRC) <a href="https://research.nvidia.com/publication/2021-06_Real-time-Neural-Radiance">[Müller et al. 2021]</a> employs a neural network that is trained in real-time to cache costly lighting calculations-->
<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.
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.
...
...
@@ -308,8 +307,8 @@ figure {
<h2>News</h2>
<hr>
<divclass="row">
<div><spanclass="material-icons">integration_instructions</span> [Jan 2022] Code released on <ahref="https://github.com/NVlabs/instant-ngp">GitHub</a>.</div>
<!-- <div><span class="material-icons"> description </span> [Jan 2022] Paper released on <a href="https://arxiv.org/abs/XXX">arXiv</a>.</div> -->
<div><spanclass="material-icons">description </span> [Jan 19th 2022] Paper released on <ahref="https://arxiv.org/abs/2201.05989">arXiv</a>.</div>
<div><spanclass="material-icons">integration_instructions</span> [Jan 14th 2022] Code released on <ahref="https://github.com/NVlabs/instant-ngp">GitHub</a>.</div>
</div>
</section>
...
...
@@ -468,8 +467,8 @@ figure {
<p>Thomas Müller, Alex Evans, Christoph Schied, Alexander Keller</p>
<div><spanclass="material-icons"> description </span><ahref="assets/mueller2022instant.pdf"> Paper preprint (PDF, 15.3 MB)</a></div>