Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Ray tracing and hybrid rasterization of Gaussian particles
| Date | Stars |
|---|---|
| 2026-07-24 | 2333 |
| 2026-07-25 | 2336 |
| 2026-07-28 | 2343 |
| 2026-07-30 | 2343 |
| 2026-08-06 | 2343 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
<p align="center"> <img height="100" src="assets/3dgrut_logo.png"> </p> --- <p align="center"> <img width="100%" src="assets/nvidia-hq-playground.gif"> </p> This repository provides the official implementations of **3D Gaussian Ray Tracing (3DGRT)** and **3D Gaussian Unscented Transform (3DGUT)**. Unlike traditional methods that rely on splatting, 3DGRT performs ray tracing of volumetric Gaussian particles instead. This enables support for distorted cameras with complex, time-dependent effects such as rolling shutters, while also efficiently simulating secondary rays required for rendering phenomena like reflection, refraction, and shadows. However, 3DGRT requires dedicated ray-tracing hardware and remains slower than 3DGS. To mitigate this limitation, we also propose 3DGUT, which enables support for distorted cameras with complex, time-dependent effects within a rasterization framework, maintaining the efficiency of rasterization methods. By aligning the rendering formulations of 3DGRT and 3DGUT, we introduce a hybrid approach called **3DGRUT**. This technique allows for rendering primary rays via rasterization and secondary rays via ray tracing, combining the strengths of both methods for improved performance and flexibility. For projects that require a fast, modular, and production-ready Gaussian Splatting framework, we recommend using [gsplat](https://github.com/nerfstudio-project/gsplat), which also provides support for 3DGUT. > __3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes__ > [Nicolas Moenne-Loccoz*](https://www.linkedin.com/in/nicolas-moënne-loccoz-71040512/?original_referer=https%3A%2F%2Fwww%2Egoogle%2Ecom%2F&originalSubdomain=ca), [Ashkan Mirzaei*](https://ashmrz.github.io), [Or Perel](https://orperel.github.io/), [Riccardo De Lutio](https://riccardodelutio.github.io/), [Janick Martinez Esturo](https://jme.pub/), > [Gavriel State](https://www.linkedin.com/in/gavstate/?originalSubdomain=ca), [Sanja Fidler](https://www.cs.utoronto.ca/~fidler/), [Nicholas Sharp^](https://nmwsharp.com/), [Zan Gojcic^](https://zgojcic.github.io/) _(*,^ indicates equal contribution)_ > _SIGGRAPH Asia 2024 (Journal Track)_ > __[Project page](https://research.nvidia.com/labs/toronto-ai/3DGRT) / [Paper](https://research.nvidia.com/labs/toronto-ai/3DGRT/res/3dgrt_compressed.pdf) / [Video](https://research.nvidia.com/labs/toronto-ai/3DGRT/res/3dgrt_supplementary_video.mp4) / [BibTeX](assets/3dgrt2024.bib)__ > __3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting__ > [Qi Wu*](https://wilsoncernwq.github.io/), [Janick Martinez Esturo*](https://jme.pub/), [Ashkan Mirzaei](https://ashmrz.github.io), > [Nicolas Moenne-Loccoz](https://www.linkedin.com/in/nicolas-moënne-loccoz-71040512/?original_referer=https%3A%2F%2Fwww%2Egoogle%2Ecom%2F&originalSubdomain=ca), [Zan Gojcic](https://zgojcic.github.io/) _(* indicates equal contribution)_ > _CVPR 2025 (Oral)_ > __[Project page](https://research.nvidia.com/labs/toronto-ai/3DGUT) / [Paper](https://research.nvidia.com/labs/toronto-ai/3DGUT/res/3DGUT_ready_main.pdf) / [Video](https://research.nvidia.com/labs/toronto-ai/3DGUT/#supp_video) / [BibTeX](assets/3dgut2025.bib)__ > __Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction__ > Jorge Condor, Nicolas Moenne-Loccoz, Merlin Nimier-David, Piotr Didyk, Zan Gojcic, Qi Wu > _arXiv 2026_ > __[Project page](https://research.nvidia.com/labs/sil/projects/neural-harmonic-textures/) / [Paper](https://research.nvidia.com/labs/sil/projects/neural-harmonic-textures/assets/neural_harmonic_textures.pdf) / [Video](https://research.nvidia.com/labs/sil/projects/neural-harmonic-textures/videos/video_nht_titleless.mp4) / [BibTeX](assets/nht2026.bib)__ ## 🔥 News - ✅[2026/06] 3DGRUT v2.0.0: Neural Harmonic Textures support. - ✅[2026/03] NCore v4: Support for training from NCore v4 datasets ([NCore](https://github.com/NVIDIA/ncore), [commands](#training-on-ncor
Excerpt of 28,733 characters
Read on GitHub
75
62
Or Perel
15
11
8
Nicholas Sharp · United States
6
5
4
4
3
2
Masahiro Ogawa
2
1
1
1
1
1
Johnny · NVIDIA · Spain
1
1
@voxel51
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:2c7a800bfa10bc49, topic:computer-vision, topic:gaussian-splatting, topic:3d-reconstruction