3D Gaussian Splatting as Markov Chain Monte Carlo (Packaged Python Version)

This repository contains the refactored Python code for 3dgs-mcmc. It is forked from commit 7b4fc9f76a1c7b775f69603cb96e70f80c7e6d13. The original code has been refactored to follow the standard Python package structure, while maintaining the same algorithms as the original version.

Features

Code organized as a standard Python package
Markov Chain Monte Carlo trainer for 3D Gaussian Splatting
Integration with reduced-3dgs

Prerequisites

Pytorch (v2.4 or higher recommended)
CUDA Toolkit (12.4 recommended, should match with PyTorch version)
(Optional) cuML for faster vector quantization

(Optional) If you have trouble with gaussian-splatting and reduced-3dgs, try to install it from source:

pip install wheel setuptools
pip install --upgrade git+https://github.com/yindaheng98/gaussian-splatting.git@master --no-build-isolation
pip install --upgrade git+https://github.com/yindaheng98/reduced-3dgs.git@main --no-build-isolation

PyPI Install

pip install --upgrade gaussian-splatting-mcmc

or build latest from source:

pip install wheel setuptools
pip install --upgrade git+https://github.com/yindaheng98/3dgs-mcmc.git@main --no-build-isolation

Development Install

git clone --recursive https://github.com/yindaheng98/reduced-3dgs
cd 3dgs-mcmc
pip install --target . --upgrade --no-deps .

Quick Start

Download dataset (T&T+DB COLMAP dataset, size 650MB):

wget https://repo-sam.inria.fr/fungraph/3d-gaussian-splatting/datasets/input/tandt_db.zip -P ./data
unzip data/tandt_db.zip -d data/

Train 3DGS-MCMC:

python -m gaussian_splatting_mcmc.train -s data/truck -d output/truck -i 30000 --mode base

Render:

python -m gaussian_splatting.render -s data/truck -d output/truck -i 30000 --load_camera output/truck/cameras.json

NeurIPS 2024 SPOTLIGHT

3D Gaussian Splatting as Markov Chain Monte Carlo

Shakiba Kheradmand, Daniel Rebain, Gopal Sharma, Weiwei Sun, Yang-Che Tseng, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, Kwang Moo Yi

BibTeX

@inproceedings{kheradmand20243d,
    title = {3D Gaussian Splatting as Markov Chain Monte Carlo},
    author = {Kheradmand, Shakiba and Rebain, Daniel and Sharma, Gopal and Sun, Weiwei and Tseng, Yang-Che and Isack, Hossam and Kar, Abhishek and Tagliasacchi, Andrea and Yi, Kwang Moo},
    booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    year = {2024},
    note = {Spotlight Presentation},
   }

Release files for gaussian-splatting-mcmc 1.3.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for gaussian-splatting-mcmc 1.3.2
File	Size	Uploaded
gaussian_splatting_mcmc-1.3.2.tar.gz	15.2 kB	May 19, 2026	Details

Built distributions (wheels)

Table of built distributions (wheels) for gaussian-splatting-mcmc 1.3.2
File	Interpreter	ABI	Platform	Reset
gaussian_splatting_mcmc-1.3.2-cp312-cp312-win_amd64.whl 123.0 kB May 19, 2026	CPython 3.12	CPython 3.12	Windows x86-64	Details
gaussian_splatting_mcmc-1.3.2-cp311-cp311-win_amd64.whl 122.3 kB May 19, 2026	CPython 3.11	CPython 3.11	Windows x86-64	Details
gaussian_splatting_mcmc-1.3.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl 3.7 MB May 19, 2026	CPython 3.11	CPython 3.11	Linux glibc 2.17+ x86-64	Details
gaussian_splatting_mcmc-1.3.2-cp310-cp310-win_amd64.whl 121.2 kB May 19, 2026	CPython 3.10	CPython 3.10	Windows x86-64	Details
gaussian_splatting_mcmc-1.3.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl 3.7 MB May 19, 2026	CPython 3.10	CPython 3.10	Linux glibc 2.17+ x86-64	Details

Total release size: 7.7 MB

Release files / gaussian_splatting_mcmc-1.3.2.tar.gz

Download URL	gaussian_splatting_mcmc-1.3.2.tar.gz
Size	15.2 kB
Tags	Source
SHA-256 checksum How to use checksums	`4824918558eb84107bd83827f3b2236fc7f14258f11fe9b1598058eec59c438d`
BLAKE2b-256 checksum How to use checksums	`bdca6c997b46194646c73ae7c11c9c8942ef4158201481f21d25b1a6274942e6`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.11`

Release files / gaussian_splatting_mcmc-1.3.2-cp312-cp312-win_amd64.whl

Download URL	gaussian_splatting_mcmc-1.3.2-cp312-cp312-win_amd64.whl
Size	123.0 kB
Tags	CPython 3.12 Windows x86-64
SHA-256 checksum How to use checksums	`07d5139e09a242830892cab38eca09daa4e894c13f2bc8b09d17434cce953aa6`
BLAKE2b-256 checksum How to use checksums	`e0ecb2a4bd2429881a70b1663b6ccbda48b674cd555f601686da957dfb149695`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.12.10`

Release files / gaussian_splatting_mcmc-1.3.2-cp311-cp311-win_amd64.whl

Download URL	gaussian_splatting_mcmc-1.3.2-cp311-cp311-win_amd64.whl
Size	122.3 kB
Tags	CPython 3.11 Windows x86-64
SHA-256 checksum How to use checksums	`9d9c03b50ea92a9cc07ce684d5c4103ffbed7480cb45472755fdece069a05cd0`
BLAKE2b-256 checksum How to use checksums	`ec558394ab4b3f0b1ce9d969968d80db53b704b810424663162363740ef670b0`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.9`

Release files / gaussian_splatting_mcmc-1.3.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl

Download URL	gaussian_splatting_mcmc-1.3.2-cp311-cp311-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Size	3.7 MB
Tags	CPython 3.11 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`49b589b600d927ebe3b4a958d67990c25f2c34c41eaaa978d355bd45aec35489`
BLAKE2b-256 checksum How to use checksums	`f1e22eee475484e2aa015e8e281113c51f4e7fb45322f56407b430b28ccb3848`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.11.15`

Release files / gaussian_splatting_mcmc-1.3.2-cp310-cp310-win_amd64.whl

Download URL	gaussian_splatting_mcmc-1.3.2-cp310-cp310-win_amd64.whl
Size	121.2 kB
Tags	CPython 3.10 Windows x86-64
SHA-256 checksum How to use checksums	`a07e1eb08e78ec1ea1d1982ac3b67ac1ef0ef79136c0c68edadecb34e086bef8`
BLAKE2b-256 checksum How to use checksums	`b052a605ee8c7005f7d9ee8ed1c331f88388688886f02fd5f4b974f0a1175010`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.11`

Release files / gaussian_splatting_mcmc-1.3.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl

Download URL	gaussian_splatting_mcmc-1.3.2-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl
Size	3.7 MB
Tags	CPython 3.10 Linux glibc 2.17+ x86-64
SHA-256 checksum How to use checksums	`0ae8f4bf42b4c51bf49293440dfc4005705984793163e0881e89bc3ae292bd4d`
BLAKE2b-256 checksum How to use checksums	`4db880e3aa2e1d9cd10b78395e387a68350fc6d93df58807a4a6718150f5009a`
Upload date	May 19, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.10.20`