CorbeauSplat is an all-in-one Gaussian Splatting automation tool designed specifically for macOS Silicon . It streamlines the entire workflow from raw video/images to a fully trained and viewable 3D scene (Gaussian Splat).
This application provides a unified Graphical User Interface (GUI) to orchestrate the following steps:
- Project Management: Automatically organizes your outputs into structured project folders with images, sparse data, and checkpoints.
- Sparse Reconstruction: Automates COLMAP feature extraction, matching, and mapping. Supports Glomap as a modern alternative mapper.
- Undistortion: Automatically undistorts images for optimal training quality.
- Training: Integrates Brush to train Gaussian Splats directly on your Mac.
- Visualization: Includes a built-in tab running SuperSplat for immediate local viewing and editing of your PLY files.
- Single Image to 3D: (Bonus) Uses Apple ML Sharp to generate a 3D model from a single 2D image.
- 4DGS Preparation (Experimental): A new module to prepare 4D Gaussian Splatting datasets (Multi-camera video -> Nerfstudio format).
- 360 Extractor (Experimental): Converts equirectangular 360° videos into optimal planar image sets (Cube Map, Ring, etc.) for photogrammetry, with AI operator masking.
It is designed to be "click-and-run", handling dependency checks, process management, and session persistence for you. It also includes built-in full localization support for French, English, German, Italian, Spanish, Arabic, Russian, Chinese, and Japanese.
This program was realized through "vibecoding" with the help of Gemini 3 Pro.
It was originally created to facilitate the technical workflow for a documentary film titled "Le Corbeau". I am not a professional developer; I simply needed to automate a complex process by gathering the tools I use daily: COLMAP, the Brush app, and SuperSplat.
I share this code in all humility. I didn't originally plan to release it, but I thought that perhaps someone, somewhere on this earth, might find it useful.
As this software was built via "vibecoding" (AI-assisted coding), it is provided "as is" with no guarantees.
- macOS (Apple Silicon recommended)
- Python 3.13+ (Recommended for JIT/Performance) or Python 3.11 (Supported)
- Xcode Command Line Tools (Required for compiling custom engines like Glomap or Brush)
- Homebrew (for installing system dependencies like COLMAP and FFmpeg)
- Git
-
Clone this repository:
git clone https://github.com/freddewitt/CorbeauSplat.git cd CorbeauSplat -
Run the launcher:
./run.command
The script will automatically detect missing dependencies (Python packages, Brush, SuperSplat, Rust, Node.js, etc.) and attempt to install them for you.
- Configuration Tab:
- Select your input (Video or Folder of images).
- Define a Project Name (your files will be saved in
[Output Folder]/[Project Name]). - Click "Create COLMAP Dataset".
- Params Tab: (Optional) Tweak advanced COLMAP settings or enable Glomap.
- Upscale Tab: (Optional)
- Check "Activate Upscale Module" to install dependencies.
- Select a model (e.g., RealESRGAN_x4plus) and a scale factor (x2, x4).
- These settings will be applied during the "Create COLMAP Dataset" phase.
- Brush Tab:
- Auto-Refine: Choose "Refine" mode to resume training from the latest checkpoint.
- Presets: Use specific densification strategies (e.g., "Aggressive Densification").
- Click "Start Brush Training".
- SuperSplat Tab:
- Load your trained
.plyfile. - Click "Start Servers" to launch the viewer locally.
- Load your trained
- 4DGS Tab (Experimental):
- Check "Activate" to install the required dependencies (Nerfstudio).
- Select a folder containing your synced camera videos.
- Click "Start Process" to generate a dataset ready for 4DGS training.
- 360 Extractor Tab (Experimental):
- Activate: Install the dedicated environment (PySide6, YOLOv8).
- Convert: Extract images from 360° videos with advanced layouts (Ring, Cube Map, Fibonacci).
- AI Masking: Automatically mask the operator.
- Apple Sharp Tab (Bonus):
- Select a single source image.
- Click "Predict 3D Model" to generate a mesh using machine learning.
CorbeauSplat exposes all its features via the command line.
� See CLI.md for full command line documentation
This project stands on the shoulders of giants. A huge thank you to the creators of the core technologies used here:
- COLMAP: Structure-from-Motion and Multi-View Stereo. GitHub
- Brush: An efficient Gaussian Splatting trainer for macOS. GitHub
- SuperSplat: An amazing web-based Splat editor by PlayCanvas. GitHub
- 360Extractor: Advanced 360° video extraction tool. GitHub
- Apple ML Sharp: Machine Learning tools for Swift. GitHub
- Nerfstudio: The modular NeRF and Splatting framework (used for 4DGS data prep). GitHub
- Real-ESRGAN: AI algorithms for image restoration and enhancement. GitHub
This project is licensed under the MIT License - see the LICENSE file for details. This is the most permissive open-source license, allowing you to use, modify, and distribute this software freely.