Project page | Paper | Video | LOD Viewer (SIBR) | Web Viewer| GarageWorld Dataset
Note: The current release is for Windows 10 only.
- Visual Studio 2019
- Cmake 3.16+
- 7zip
- Python 3.8+ for shaders installation scripts and dataset preprocess scripts
- Doxygen 1.8.17+ for documentation
- CUDA 10.1+ and CUDnn if projects requires it
Make sure Python, CUDA and Doxygen are in the PATH
Checkout this repository's main branch:
## through HTTPS
git clone https://github.com/zhaofuq/LOD-SIBR-Viewer.git -b main
## through SSH
git clone [email protected]:zhaofuq/LOD-SIBR-Viewer.git -b main
cd LOD-SIBR-Viewer
cmake . -B build
cmake --build build --target install --config RealWithDebInfo
For more details, please see the official documentation: http://sibr.gitlabpages.inria.fr Run our LOD Viewer for Multi-Resolution Gaussians, using
./install/bin/SIBR_gaussianViewer_app_rwdi.exe -m <path to letsgo model path>
--render-mode lod
and our model files are structured as:
{exp-name}/
cfg_args
camera.json
point_cloud/iteration_xxx:
--level_0.ply
--level_1.ply
...
Or run original Gaussian Viewer, using
./install/bin/SIBR_gaussianViewer_app_rwdi.exe -m <path to gaussian model path> --render-mode gaussian
If you find our code or paper helps, please consider citing:
@article{cui2024letsgo,
title={LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitives},
author={Jiadi Cui, Junming Cao, Fuqiang Zhao, Zhipeng He, Yifan Chen, Yuhui Zhong, Lan Xu, Yujiao Shi, Yingliang Zhang, Jingyi Yu},
journal={arXiv preprint arXiv:2404.09748},
year={2024}
}
We will track bugs and issues through the Issues interface on gitlab. Inria gitlab does not allow creation of external accounts, so if you have an issue/bug please email [email protected]
and we will either create a guest account or create the issue on our side.
if you are the first to use a very recent Cmake version, you will have to update CHECKED_VERSION
in the root CmakeLists.txt
.
you probably selected the 32-bits compiler in Cmake-gui.
make sure Python is installed and in the path.
build and install each project separately by selecting the proper targets.
make sure CUDA >= 10.1 (first version to support VS2019) is installed.
SIBR is a System for Image-Based Rendering.
It is built around the sibr-core in this repo and several Projects implementing published research papers.
For more complete documentation, see here: SIBR Documentation
This SIBR core repository provides :
- a basic Image-Based Renderer
- a per-pixel implementation of Unstructured Lumigraph (ULR)
- several dataset tools & pipelines do process input images
@misc{sibr2020,
author = "Bonopera, Sebastien and Esnault, Jerome and Prakash, Siddhant and Rodriguez, Simon and Thonat, Theo and Benadel, Mehdi and Chaurasia, Gaurav and Philip, Julien and Drettakis, George",
title = "sibr: A System for Image Based Rendering",
year = "2020",
url = "https://gitlab.inria.fr/sibr/sibr_core"
}