#2525th of 75 in Image and videoFor image, video and design, 3d
lichtfeld-studio
Native desktop app for training and editing 3D Gaussian Splatting scenes
- Stars
- 4k
- License
- GPL-3.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- C++
2,868 on 22 Apr 20263,992 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
LichtFeld Studio is a C++23/CUDA application that trains 3D Gaussian Splatting scenes from COLMAP datasets, resumes checkpoints, and shows the reconstruction in a real-time viewer. It supports editing gaussian selections with undo/redo and exports to PLY, SOG, SPZ or a standalone HTML viewer. Python plugins, embedded Python and MCP resources and tools allow automation, and it can also run headless.
Who it is for: Researchers and 3D teams working with Gaussian Splatting on NVIDIA GPUs
Strengths
- Training, live viewer, gaussian editing and export in one application
- Exports PLY, SOG, SPZ and a standalone HTML viewer
- Python plugin system plus MCP tools for scripting and agent control
- Includes MCMC, bilateral grid, 3DGUT and optional POPSpa sparsification
Weaknesses
- Requires an NVIDIA GPU with compute capability 7.5+; AMD, Intel and older NVIDIA unsupported
- Prebuilt Windows binaries need a paid donation via the Portal, not GitHub Releases
- Needs NVIDIA driver 570+ and CUDA 12.8+; source builds need a C++23 toolchain
- No Docker or compose setup provided
What it needs
- GPU required
- Docker + Compose
- Needs NVIDIA driver 570+, CUDA 12.8+, COLMAP dataset input
- Models: 3D Gaussian Splatting, PLY, SOG, SPZ
What changed
- v0.5.4.2 ↗ (opens in a new tab)Security fix
“The private keys of eight eMudhra intermediate certificate authorities can be recovered from their certificates (disclosed on 2026-10-20). Anyone can therefore forge certificates that chain to these …”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Image and video
See all 75| Rank | Project | Score |
|---|---|---|
| 1 | frigateLocal NVR with realtime object detection for IP cameras | 93 out of 100 |
| 2 | MoneyPrinterTurboGenerates short videos from a topic, with script, footage, voiceover and subtitles | 88 out of 100 |
| 3 | toonflow-appInfinite-canvas tool for AI short drama and comic video production | 87 out of 100 |
| #4 | InvokeAIWeb UI for diffusion image generation with inpainting canvas and node workflows | 86 out of 100 |
| #5 | ComfyUINode-graph editor for running diffusion image, video, audio and 3D workflows | 85 out of 100 |