Skip to main content

Gaussian Splatting compression toolkit

Project description

Splatwizard: Gaussian Splatting Compression Toolkit

License PyPI

Splatwizard is a one-stop toolkit designed for researching 3DGS compression, dedicated to accelerating community exploration in this field. With flexible API design, you can easily combine advanced components from state-of-the-art models to build customized models. Key features of the project include:

  • Easy-to-adapt evaluation framework for new models
  • Comprehensive evaluation metrics
  • Multiple baseline models included for comparison

Latest News

  • 2025/11/25: Release first version.

Installation

Splatwizard can be installed via pip

pip install splatwizard

Since the installation process requires significant time to precompile all components, you can monitor the installation progress using the --verbose option.

pip install splatwizard --verbose

Additionally, pip compiles components in an isolated environment by default. You can use --no-build-isolation to perform the compilation directly in the current environment. Make sure torch and ninja are installed before running the command.

pip install splatwizard --verbose --no-build-isolation

To speed up compilation, the installation process uses all available CPU cores by default. If you need to limit the number of cores used for compilation, you can specify the maximum cores used via environment variable MAX_BUILD_JOBS. The following command will use up to 8 CPU cores during compilation.

MAX_BUILD_JOBS=8 pip install splatwizard --verbose --no-build-isolation

Quick start

Train your first 3DGS model in splatwizard

sw-train \
    --source_path /data/MipNeRF-360/bicycle \
    --output_dir /output/gs \                  
    --model 3dgs \
    --optim 3dgs

Evaluate model

sw-eval \
    --source_path /data/MipNeRF-360/bicycle \
    --output_dir /output/gs \                  
    --model 3dgs \
    --optim 3dgs \
    --checkpoint /output/gs/checkpoints/ckpt30000.pth

For more models. please check Model List

Documentation

License

Splatwizard is licensed under the MIT License. The project incorporates code from other projects, which remains under their original licenses.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

splatwizard-0.0.5.tar.gz (2.0 MB view details)

Uploaded Source

File details

Details for the file splatwizard-0.0.5.tar.gz.

File metadata

  • Download URL: splatwizard-0.0.5.tar.gz
  • Upload date:
  • Size: 2.0 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.14

File hashes

Hashes for splatwizard-0.0.5.tar.gz
Algorithm Hash digest
SHA256 5c9ded0370b09ed94661e7641af4c11cb6d6ee0325e2a16119c1275e9f4ebb44
MD5 2c9c625ee673871fbafc2b6176ec3b54
BLAKE2b-256 38c95037f306e2667912fe04f4ca40289065c6d71eb578e11e9e1c045c84a653

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page