FriendlySplat
FriendlySplat is a user-friendly, open-source Gaussian Splatting toolkit, integrating SOTA features into a unified platform for training, pruning, meshing and segmentation.
File Explorer
Download Latest Version (.zip)- Differential Robotics.png
- FastLab.png
- logo.png
- test_garden.npz
- why-friendlysplat-v2.gif
- Zhejiang University.png
- eval.py
- config.py
- run.py
- preprocess_dtu_batch.py
- preprocess_tnt_batch.py
- README.md
- run_eval_dtu_batch.py
- run_eval_tnt_batch.py
- run_train_dtu_batch.py
- run_train_tnt_batch.py
- README.md
- run_eval_batch.py
- run_train_batch.py
- README.md
- run_eval_batch.py
- run_train_batch.py
- eval_single_scene.py
- merge_partitions_ckpt.py
- partition_from_coarse.py
- preprocess_gauu_batch.py
- README.md
- run_gauu_benchmark.sh
- run_matrixcity_coarse.sh
- run_matrixcity_partition_train.sh
- summarize_gauu_benchmark.py
- summarize_matrixcity_benchmark.py
- __init__.py
- base_dataparser.py
- colmap_dataparser.py
- colmap_io.py
- dataloader.py
- dataset.py
- image_io.py
- scene_transform.py
- __init__.py
- bilateral_grid.py
- gaussian.py
- pose_opt.py
- __init__.py
- renderer.py
- __init__.py
- builder.py
- configs.py
- eval_runtime.py
- gns_pruning.py
- io_utils.py
- logger.py
- losses.py
- optimizer_coordinator.py
- speedy_pruning.py
- step_runtime.py
- step_schedule.py
- __init__.py
- lpips.py
- networks.py
- utils.py
- __init__.py
- __init__.py
- gaussian_transforms.py
- metrics.py
- __init__.py
- gsplat_viewer.py
- nerfview_render_panel.py
- viewer_panels.py
- viewer_renderer.py
- viewer_runtime.py
- __init__.py
- train_app.py
- view_app.py
- __init__.py
- png_compression.py
- sog_kmeans.py
- sog_quantization.py
- sort.py
- glm
- Adam.cpp
- Adam.h
- AdamCUDA.cu
- Intersect.cpp
- Intersect.h
- IntersectTile.cu
- Null.cpp
- Null.h
- NullCUDA.cu
- Projection.cpp
- Projection.h
- Projection2DGS.cuh
- Projection2DGSFused.cu
- Projection2DGSPacked.cu
- ProjectionEWA3DGSFused.cu
- ProjectionEWA3DGSPacked.cu
- ProjectionEWASimple.cu
- ProjectionUT3DGSFused.cu
- QuatScaleToCovar.cpp
- QuatScaleToCovar.h
- QuatScaleToCovarCUDA.cu
- Rasterization.cpp
- Rasterization.h
- RasterizeToIndices2DGS.cu
- RasterizeToIndices3DGS.cu
- RasterizeToPixels2DGSBwd.cu
- RasterizeToPixels2DGSFwd.cu
- RasterizeToPixels3DGSBwd.cu
- RasterizeToPixels3DGSFwd.cu
- RasterizeToPixelsFromWorld3DGSBwd.cu
- RasterizeToPixelsFromWorld3DGSFwd.cu
- Relocation.cpp
- Relocation.h
- RelocationCUDA.cu
- SphericalHarmonics.cpp
- SphericalHarmonics.h
- SphericalHarmonicsCUDA.cu
- Cameras.cuh
- Cameras.h
- Common.h
- Ops.h
- Utils.cuh
- __init__.py
- _backend.py
- _torch_impl.py
- _torch_impl_2dgs.py
- _wrapper.py
- ext.cpp
- __init__.py
- selective_adam.py
- __init__.py
- base.py
- default.py
- improved.py
- mcmc.py
- ops.py
- __init__.py
- _helper.py
- distributed.py
- exporter.py
- profile.py
- relocation.py
- rendering.py
- sog_exporter.py
- utils.py
- version.py
- convert_ply_to_sog.py
- test_median_depth_batch_render.py
- test_normals_batch_render.py
- test_sog_export.py
- __init__.py
- moge_infer.py
- README.md
- image_fitting.py
- README.md
- __init__.py
- README.md
- tsdf_mesh_from_ply.py
- __init__.py
- gauscluster_core.py
- instascene_gauscluster.py
- README.md
- __init__.py
- hloc_utils.py
- README.md
- run_hloc_sfm.py
- __init__.py
- .dockerignore
- .gitignore
- .gitmodules
- docker-compose.yml
- Dockerfile
- entrypoint.sh
- formatter.sh
- LICENSE
- MANIFEST.in
- pyproject.toml
- README.md
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/AshadowZ/FriendlySplat
Downloads the entire project code from GitHub to your computer.
cd FriendlySplat
Moves into the project folder you just downloaded.
2. Official Install Script
Easy RecommendedPrerequisites
- Python 3 Python is required to use pip.
pip install torch==2.4.0 torchvision==0.19.0 --index-url https://download.pytorch.org/whl/cu121
Installs the package published on PyPI directly β no need to clone the source.
pip install ninja
Installs the package published on PyPI directly β no need to clone the source.
After installing, open a new terminal and run the program's version command (e.g. --version) to confirm it worked.
Pulled directly from this repo's README.
3. Docker
EasyPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build --build-arg TORCH_CUDA_ARCH_LIST="8.9" -t friendlysplat:latest .
Builds a runnable image based on the Dockerfile.
docker run --gpus all -it --rm \
Runs the built image as an actual container.
docker compose run --rm friendlysplat
Runs the command against the services defined in the compose file.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
Pulled directly from this repo's README.
4. Python
EasyPrerequisites
pip install torch==2.4.0 torchvision==0.19.0 --index-url https://download.pytorch.org/whl/cu121
Installs the package published on PyPI directly β no need to clone the source.
pip install ninja
Installs the package published on PyPI directly β no need to clone the source.
pip install -e ".[train,viewer]" --no-build-isolation
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)