Skip to main content

NVIDIA 3D Gaussian Splat to USD Converter

Project description

Omniverse Gaussian Splat Converter

A pip-installable Python package for converting 3D Gaussian Splat data (PLY and SPZ formats) to USD using the ParticleField3DGaussianSplat schema.

Installation

pip install omniverse-gsplat-converter

For USD support (if not already installed):

pip install omniverse-gsplat-converter[usd]

Usage

Command Line

# Convert a PLY file to USDZ
omni_gsplat_convert -i input.ply -o output.usdz

# Convert an SPZ file to USDA with Z-up axis
omni_gsplat_convert -i input.spz -o output.usda --up-axis Z

# Generate spherical harmonics and scales from raw PLY
omni_gsplat_convert -i input.ply -o output.usdz --generateSh --generateScales

You can also run via python -m:

python -m omniverse_gsplat_converter -i input.ply -o output.usdz

Python API

from omniverse_gsplat_converter import read_ply, read_spz, write_gaussian_splat_usd

# Read a PLY file
splat_data = read_ply("scene.ply")

# Write to USD
write_gaussian_splat_usd(splat_data, "scene.usdz", source_file="scene.ply")

# Read an SPZ file
splat_data = read_spz("scene.spz")

# Write to USD with options
write_gaussian_splat_usd(
    splat_data,
    "scene.usda",
    source_file="scene.spz",
    up_axis="Z",
    rotation_degrees=(90.0, 0.0, 0.0),
)

Project details


Download files

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

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

omniverse_gsplat_converter-0.1.1-py3-none-any.whl (18.4 kB view details)

Uploaded Python 3

File details

Details for the file omniverse_gsplat_converter-0.1.1-py3-none-any.whl.

File metadata

File hashes

Hashes for omniverse_gsplat_converter-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 022b458109bd78290fa4d6a18b47fd601a34a58b7e10d6a816073cb69adc5e91
MD5 c05780ca7eaf686cc9d4776700c2da18
BLAKE2b-256 91da28117aa1e5eb1364288d80e800dc97470f59a36f49675db42b06608eb139

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