Meshroom is an open-source, node-based visual programming framework—a flexible toolbox for creating, managing, and executing complex data processing pipelines.
Meshroom uses a nodal system where each node represents a specific operation, and output attributes can seamlessly feed into subsequent steps. When a node’s attribute is modified, only the affected downstream nodes are invalidated, while cached intermediate results are reused to minimize unnecessary computation.
Meshroom supports both local and distributed execution, enabling efficient parallel processing on render farms.
It also includes interactive widgets for visualizing images and 3D data. Official releases come with built-in plugins for computer vision and machine learning tasks.
Get the project
You can download pre-compiled binaries for the latest release.
If you want to build it yourself, see INSTALL.md to setup the project and pre-requisites.
To use Meshroom with custom plugins, see INSTALL_PLUGINS.md.
Concepts
- Graph: A collection of interconnected nodes that defines the sequence of operations to represent your complete data processing workflow.
- Nodes: The fundamental building blocks, each performing a specific task. Nodes are connected through edges that represent the flow of data between them.
- Attributes: Parameters that control how each node behaves. When an attribute is modified, it triggers the invalidation of all connected downstream nodes while preserving cached intermediate results.
- Templates: Ready-to-use pipeline configurations provided by plugins. You can customize existing templates or create and save your own.
- Local / Renderfarm: Choose between local processing or distributed computation on render farms. You can monitor progress, review logs, track resource consumption, and use both modes simultaneously as Meshroom manages node locking during external computation.
- Custom Plugins: Extend Meshroom's capabilities by creating your own nodes in Python or by integrating external command-line tools.
User Interface
The Meshroom UI is divided into several key areas:
- Graph Editor: The central area where nodes are placed and connected to form a processing pipeline.
- Node Editor: It contains multiple tabs with:
- Attributes: Displays the attributes and parameters of the selected node.
- Log: Displays execution logs and error messages.
- Statistics: Displays resource consumption
- Status: Display some technical information on the node (workstation, start/end time, etc.)
- Documentation: Node Documentation.
- Notes: Change label or put some notes on the node to know why it’s used in this graph.
- 2D & 3D Viewer: Visualizes the output of certain nodes.
- Image Gallery: Visualize the list of input files.
Manual and Tutorials
Plugins bundled by default
AliceVision Plugin
AliceVision Website
AliceVision Repository
AliceVision provides state-of-the-art 3D Computer Vision and Machine Learning algorithms that analyze and understand image content to transform collections of regular 2D photographs into detailed 3D models, camera positions, and scene geometry. Born from collaboration between academia and industry, it delivers research-grade algorithms with production-level robustness and quality.
The AliceVision plugin offers comprehensive pipelines for:
- 3D Reconstruction from multi-view images (pipeline overview, results on Sketchfab)
- Camera Tracking for camera motion estimation
- HDR Fusion from multi-bracketed photography
- Panorama Stitching including fisheye support and motorized head systems
- Photometric Stereo for geometric reconstruction from a single view with multiple lightings
- Multi-View Photometric Stereo combining photogrammetry with photometric stereo
Segmentation Plugin
MrSegmentation: A set of nodes for AI-powered image segmentation from natural language prompts. The plugin leverages foundation models to automatically identify and isolate specific objects or regions in images based on textual descriptions, enabling intuitive content-aware processing workflows.
Other plugins
See MeshroomHub for more plugins.
DepthEstimation Plugin
MrDepthEstimation: A set of nodes for AI-based monocular depth estimation from image sequences. The plugin leverages deep learning models to predict depth information from single images, enabling depth estimation in new scenarios.
RoMa Plugin
MrRoma: A set of nodes for RoMa (robust dense feature matching).
The plugin leverages foundation models to provide pixel-dense correspondence estimation with reliable certainty maps, enabling robust matching even under extreme variations in scale, illumination, viewpoint, and texture.
This is the beginning of the README. Read the rest at the original. Read the full README ↗
