After having totally forgotten about that in some personal crazy-times after Siggraph, I've finally uploaded the Tutorial slides to our Siggraph 26 OptiX/OWL course to github.com/ingowald/Siggraph… . Apologies for the late upload!
Nate Morrical retweeted
New AMD graphics research: "Ray Tracing Massive Amounts of Animated Geometry" 🌳
🔺 Tetrahedral cages decouple animation cost from triangle count.
⚡ Enables massive animated scenes in real-time ray tracing.
Read more ⬇️
gpuopen.com/learn/ray-tracin…
Nate Morrical retweeted
Ordered Front-to-back Any-Hit Traversal in RTX
Ingo Wald
arxiv.org/abs/2605.16697 [𝚌𝚜.𝙶𝚁 𝚌𝚜.𝙲𝙶]
I often use Inigo's sdBoxFrame SDF for debugging marchers, but found it odd there's no readily available iBoxFrame ray intersector equivalent.
So I made one!
shadertoy.com/view/7cf3Dj
Nate Morrical retweeted
I'd like to share @DaqiLin and I co-authored a chapter in the latest GPU Zen 4 book.
We cover the engineering details of implementing ReSTIR GI & PT in UE5's NvRTX branch, adopted in NVIDIA's Zorah project showcased at CES and GDC last year.
The book is now available on Amazon.
Nate Morrical retweeted
In 2026, I reprise my role as High-Performance Graphics papers chair, joined by @nmkettunen.
The papers deadline is 8 weeks from now. Submit your performance-oriented graphics research and present it in Los Angeles, just before SIGGRAPH (July 17-19 2026)!
highperformancegraphics.org/…
Nate Morrical retweeted
In this paper is proposed Gabor Fields, a new volumetric primitive fields that enables continuous frequency filtering at no cost, enabling continuous LoD control, reduced rendering time, and a trade-off between variance and bias for performance.
arxiv.org/pdf/2602.05081
Nate Morrical retweeted
Excited to share our new paper, “Materializing Inter-Channel Relationships with Multi-Density Woodcock Tracking,” IEEE TVCG! (to appear)
Huge thanks to my co-authors: @stefanzellmann , Haichao Miao, @NateMorrical , @IngoWald , @PascucciValerio
Preprint: alpers-git.github.io/persona…
Nate Morrical retweeted
research.nvidia.com/labs/rtr…
"ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths"
Nate Morrical retweeted
I am excited to share our #SIGGRAPHAsia2025 ToG paper, co-authored with Eugene d'Eon, @rohansawhney1, and my PhD advisor @wkjarosz. We introduce a new method that accelerates Walk on Spheres (WoS) by orders of magnitude.
Nate Morrical retweeted
I am excited to announce the release of Radical Pie, version 1.0! This is the professional equation typesetting application that I've been working on for the last year. See the website for details.
radicalpie.com/
Nate Morrical retweeted
🌲Introducing our paper A generalizable light transport 3D embedding for Global Illumination arxiv.org/pdf/2510.18189.
Just as Transformers learn long-range relationships between words or pixels, our new paper shows they can also learn how light interacts and bounces around a 3D scene.
Building on the analogy of light transport operator and Attention, our fully scalable model learns a generalizable light transport 3D embedding that captures global illumination.
It takes as input the 3D scene assets—geometry, materials, and lighting represented as a point cloud—and encodes the complex light interaction into a 3D latent space, with codes anchored at the sampled scene points.
Remarkably, the model is independent of both viewpoint and resolution, enabling view-consistent rendering across diverse scenes. (See teaser and attention figure.)
(Our team work: with my mentor Marco @marcosalvi, labmates Mukund @mukundvermar, Cheng, NV folks Bart @BartWronsk, Lifan @winmad4869, and Tzu-Mao @tzumaoli & Ravi.)
🧵
Nate Morrical retweeted
GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting
Contributions:
• We introduce a novel radiance cache optimized for volume rendering that caches path-space radiance using multiple levels of Gaussian splats.
• The cache works in real time on complex datasets and in a wide variety of use cases. It adapts quickly to changes in the transfer function and lighting parameters, improving overall image quality and rendering times.
• Optimizing the cache is possible not only with clean samples but also with noisy data, as is commonly found in Monte-Carlo-based renderers.
• The path-space nature of the cache and its non-invasive design make it easy to use and integrate into existing rendering solutions.
Nate Morrical retweeted
📢📢We have a last-minute internship opening on my team at @NVIDIAAI for this summer. If you are interested and have experience with large feedforward reconstruction models or post-training image/video diffusion models, please get in touch!
Nate Morrical retweeted
Our upcoming HPG 2025 paper ”Collaborative Texture Filtering” is up!
Research done with
@_pandersson, Matt Pharr, and @BartWronsk.
research.nvidia.com/labs/rtr…
Nate Morrical retweeted
SOBB: Skewed Oriented Bounding Boxes for Ray Tracing
Kácerik Martin, Bittner Jirí
diglib.eg.org/items/f17ede08…
Abstract
We propose skewed oriented bounding boxes (SOBB) as a novel bounding primitive for accelerating the calculation of rayscene intersections. SOBBs have the same memory footprint as the well-known oriented bounding boxes (OBB) and can be used with a similar ray intersection algorithm. We propose an efficient algorithm for constructing a BVH with SOBBs, using a transformation from a standard BVH built for axis-aligned bounding boxes (AABB). We use discrete orientation polytopes as a temporary bounding representation to find tightly fitting SOBBs. Additionally, we propose a compression scheme for SOBBs that makes their memory requirements comparable to those of AABBs. For secondary rays, the SOBB BVH provides a ray tracing speedup of 1.0-11.0x over the AABB BVH and it is 1.1x faster than the OBB BVH on average. The transformation of AABB BVH to SOBB BVH is, on average, 2.6x faster than the ditetrahedron-based AABB BVH to OBB BVH transformation.
Nate Morrical retweeted
The rationale for reservoir sampling wasn't clicking for me but then someone wrote this samwho.dev/reservoir-samplin… Thank you @samwhoo
Nate Morrical retweeted
Alan Wolfe, William Donnelly, and Henrik Halén,
Importance-Sampled Filter-Adapted Spatio-Temporal Sampling
jcgt.org/published/0014/01/0…
If you’ve ever wanted to train your own gaussian dataset, this handy new framework just went live: github.com/nv-tlabs/3dgrut







































