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, maintaing 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.
3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes
Nicolas Moenne-Loccoz*, Ashkan Mirzaei*, Or Perel, Riccardo De Lutio, Janick Martinez Esturo,
Gavriel State, Sanja Fidler, Nicholas Sharp^, Zan Gojcic^ (*,^ indicates equal contribution)
SIGGRAPH Asia 2024 (Journal Track)
Project page / Paper / Video / BibTeX
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
Qi Wu*, Janick Martinez Esturo*, Ashkan Mirzaei,
Nicolas Moenne-Loccoz, Zan Gojcic (* indicates equal contribution)
CVPR 2025
Project page / Paper / Video / BibTeX
- ✅[2025/03] Initial code release!
- ✅[2025/02] 3DGUT was accepted to CVPR 2025!
- ✅[2024/08] 3DGRT was accepted to SIGGRAPH Asia 2024!
- 🔥 News
- Contents
- 🔧 1 Dependencies and Installation
- 💻 2. Train 3DGRT or 3DGUT scenes
- 🎥 3. Rendering from Checkpoints
- 📋 4. Evaluations
- 🛝 5. Interactive Playground GUI
- 🎓 6. Citations
- 🙏 7. Acknowledgements
- CUDA 11.8+ Compatible System
- For good performance with 3DGRT, we recommend using an NVIDIA GPU with Ray Tracing (RT) cores.
- Currently, only Linux environments are supported by the included install script (Windows support coming soon!)
NOTE: gcc versions >11 (expand for details)
Currently the codebase requires gcc <= 11. If your machine uses the compiler gcc-12 or newer (i.e., in Ubuntu 24.04), you may need to install and use gcc-11.
First, install gcc 11:
sudo apt-get install gcc-11 g++-11Then run the install script with the optional WITH_GCC11 flag, which additionally configures the conda environment to use gcc-11:
./install_env.sh 3dgrut WITH_GCC11To set up the environment using conda, first clone the repository and run ./install_env.sh script as:
git clone --recursive https://github.com/nv-tlabs/3dgrut.git
cd 3dgrut
# You can install each components step by step following install_env.sh
chmod +x install_env.sh
./install_env.sh 3dgrut
conda activate 3dgrutWe provide different configurations for training using 3DGRT and 3DGUT models on common benchmark datasets. For example you can download NeRF Synetic dataset, MipNeRF360 dataset or ScanNet++, and then run one of the following commands:
# Train Lego with 3DGRT & 3DGUT
python train.py --config-name apps/nerf_synthetic_3dgrt.yaml path=data/nerf_synthetic/lego out_dir=runs experiment_name=lego_3dgrt
python train.py --config-name apps/nerf_synthetic_3dgut.yaml path=data/nerf_synthetic/lego out_dir=runs experiment_name=lego_3dgut
# Train Bonsai
python train.py --config-name apps/colmap_3dgrt.yaml path=data/mipnerf360/bonsai out_dir=runs experiment_name=bonsai_3dgrt dataset.downsample_factor=2
python train.py --config-name apps/colmap_3dgut.yaml path=data/mipnerf360/bonsai out_dir=runs experiment_name=bonsai_3dgut dataset.downsample_factor=2
# Train Scannet++
python train.py --config-name apps/scannetpp_3dgut.yaml path=data/scannetpp/0a5c013435/dslr out_dir=runs experiment_name=0a5c013435_3dgutNote
For ScanNet++, we expect the dataset to be preprocessed following FisheyeGS's method.
Note
If you're running from PyCharm IDE, enable rich console through: Run Configuration > Modify Options > Emulate terminal in output console*
Evaluate Checkpoint with Splatting / OptiX Tracer / Torch
python render.py --checkpoint runs/lego/ckpt_last.pt --out-dir outputs/evalpython train.py --config-name apps/nerf_synthetic_3dgut.yaml path=data/nerf_synthetic/lego with_gui=True python train.py --config-name apps/nerf_synthetic_3dgut.yaml path=data/nerf_synthetic/lego with_gui=True test_last=False export_ingp.enabled=False resume=runs/lego/ckpt_last.pt Note
Remember to set DISPLAY environment variable if you are running on a remote server
On start up, you might see a black screen, but you can use the GUI to navigate to correct camera views:
We provide scripts to reproduces results reported in publications.
# Training
bash ./benchmark/mipnerf360_3dgut.sh <config-yaml>
# Rendering
bash ./benchmark/mipnerf360_3dgut_render.sh <config-yaml>bash ./benchmark/mipnerf360.sh paper/3dgut/unsorted_colmap.yamlResults for unsorted 3DGUT (Produced on RTX 5090):
| Bicycle | Bonsai | Counter | Flower | Garden | Kitchen | Room | Stump | Treehill | Average | |
|---|---|---|---|---|---|---|---|---|---|---|
| train(s) | 835.93 | 476.00 | 468.86 | 681.15 | 665.59 | 502.89 | 447.66 | 682.58 | 669.83 | 608.28 |
| FPS | 269.5 | 362.3 | 336.7 | 276.2 | 333.3 | 310.6 | 383.1 | 333.3 | 326.8 | 325.8 |
| PSNR | 24.737 | 32.235 | 28.448 | 21.326 | 26.699 | 30.393 | 31.130 | 26.289 | 22.518 | 27.086 |
bash ./benchmark/scannetpp.sh paper/3dgut/unsorted_scannetpp.yamlNote
We followed FisheyeGS's convention to prepare the dataset for fair comparisons
Results for unsorted 3DGUT (Produced on RTX 5090):
| 0a5c013435 | 8d563fc2cc | bb87c292ad | d415cc449b | e8ea9b4da8 | fe1733741f | Average | |
|---|---|---|---|---|---|---|---|
| train(s) | 298.09 | 295.64 | 330.89 | 405.95 | 288.53 | 371.71 | 331.80 |
| FPS | 408.2 | 465.1 | 490.2 | 446.4 | 401.6 | 444.4 | 442.7 |
| PSNR | 29.790 | 26.848 | 31.610 | 28.084 | 33.259 | 25.608 | 29.200 |
The playground allows interactive exploration of pretrained scenes, with raytracing effects such as inserted object, reflections, refractions, depth of field, and more.
Run the playground UI to visualize a pretrained scene with:
python playground.py --gs_object <ckpt_path>
See Playground README for details.
@article{loccoz20243dgrt,
author = {Nicolas Moenne-Loccoz and Ashkan Mirzaei and Or Perel and Riccardo de Lutio and Janick Martinez Esturo and Gavriel State and Sanja Fidler and Nicholas Sharp and Zan Gojcic},
title = {3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes},
journal = {ACM Transactions on Graphics and SIGGRAPH Asia},
year = {2024},
}
@article{wu20253dgut,
title={3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting},
author={Wu, Qi and Martinez Esturo, Janick and Mirzaei, Ashkan and Moenne-Loccoz, Nicolas and Gojcic, Zan},
journal = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2025}
}
We sincerely thank our colleagues for their valuable contributions to this project.
Hassan Abu Alhaija, Ronnie Sharif, Beau Perschall and Lars Fabiunke for assistance with assets. Greg Muthler, Magnus Andersson, Maksim Eisenstein, Tanki Zhang, Nathan Morrical, Dietger van Antwerpen and John Burgess for performance feedback. Thomas Müller, Merlin Nimier-David, and Carsten Kolve for inspiration and pointers. Ziyu Chen, Clement Fuji-Tsang, Masha Shugrina, and George Kopanas for technical & experiment assistance, and to Ramana Kiran and Shailesh Mishra for typo fixes.
