Skip to content

MrNeRF/LichtFeld-Studio

Repository files navigation

LichtFeld Studio
**A high-performance C++ and CUDA implementation of 3D Gaussian Splatting**

Discord Website Papers License CUDA C++

3D Gaussian Splatting Viewer

OverviewCommunity & SupportInstallationContributingAcknowledgmentsCitationLicense


Sponsors


Support LichtFeld Studio Development

LichtFeld Studio is a free, open-source implementation of 3D Gaussian Splatting that pushes the boundaries of real-time rendering performance.

Why Your Support Matters: This project requires significant time and resources to develop and maintain.

Unlike commercial alternatives that can cost thousands in licensing fees, LichtFeld Studio remains completely free and open. Your contribution helps ensure it stays that way while continuing to evolve with the latest research.

Whether you're using it for research, production, or learning, your support enables us to dedicate more time to making LichtFeld Studio faster, more powerful, and accessible to everyone in the 3D graphics community.

PayPal Support on Donorbox


Overview

LichtFeld Studio is a high-performance implementation of 3D Gaussian Splatting that leverages modern C++23 and CUDA 12.8+ for optimal performance. Built with a modular architecture, it provides both training and real-time visualization capabilities for neural rendering research and applications.

Key Features

  • 2.4x faster rasterization (winner of first bounty by Florian Hahlbohm)
  • MCMC optimization strategy for improved convergence
  • Real-time interactive viewer with OpenGL rendering
  • Modular architecture with separate core, training, and rendering components
  • Multiple rendering modes including RGB, depth, and combined views
  • Bilateral grid appearance modeling for handling per-image variations

Community & Support

Join our growing community for discussions, support, and updates:

Installation

Find out how to install in our LichtFeld Studio Wiki

Contributing

We welcome contributions! See our Contributing Guidelines.

Getting Started

  • Check issues labeled good first issue
  • Join our Discord for discussions
  • Use the pre-commit hook: cp tools/pre-commit .git/hooks/

Acknowledgments

This project builds upon and is inspired by the following:

Core Research

Project Description License
3D Gaussian Splatting Original work by Kerbl et al. Custom
gsplat Optimized CUDA rasterization backend Apache-2.0

Gaussian Splatting Tools & Inspiration

Project Description License
SuperSplat PlayCanvas Gaussian Splat editor MIT
SplatShop Gaussian Splat editing tool MIT
splat-transform Transformation utilities for splats MIT
spz Niantic's compressed splat format MIT

Graphics & UI Libraries

Project Description License
Dear ImGui Immediate mode GUI library MIT
ImGuizmo Gizmo manipulation for ImGui MIT
GLFW OpenGL window/context management zlib
GLM OpenGL Mathematics library MIT
glad OpenGL loader MIT

CUDA & GPU Libraries

Project Description License
NVIDIA nvImageCodec GPU-accelerated image encoding/decoding Apache-2.0
Intel TBB Threading Building Blocks Apache-2.0

Data & I/O Libraries

Project Description License
tinyply Lightweight PLY file loader Public Domain / BSD-2
OpenImageIO Image I/O library Apache-2.0
nlohmann/json JSON for Modern C++ MIT
LibArchive Multi-format archive library BSD
libwebp WebP image format library BSD-3-Clause

Utilities

Project Description License
spdlog Fast C++ logging library MIT
cpp-httplib HTTP/HTTPS library MIT
FreeType Font rendering library FreeType License
args Command-line argument parser MIT

Testing & Development

Project Description License
PyTorch/LibTorch Used for tensor comparison tests BSD-3-Clause
Google Test C++ testing framework BSD-3-Clause

Icons

Project Description License
Tabler Icons UI icons MIT
Lucide Icons UI icons (fork of Feather) ISC

Citation

@software{lichtfeld2025,
  author    = {LichtFeld Studio},
  title     = {A high-performance C++ and CUDA implementation of 3D Gaussian Splatting},
  year      = {2025},
  url       = {https://github.com/MrNeRF/LichtFeld-Studio}
}

License

This project is licensed under GPLv3. See LICENSE for details.


Connect with us: WebsiteDiscordTwitter