Meshroom is a node-based photogrammetry software designed to transform collections of two-dimensional images into three-dimensional models and scene geometry. It provides a visual interface for constructing and managing modular data pipelines, allowing users to automate complex computer vision tasks such as feature extraction, depth map estimation, and mesh generation.
The software distinguishes itself through a distributed computational framework that dispatches resource-intensive tasks across local hardware or remote render farms. By utilizing a directed acyclic graph execution model, it enables granular control over processing sequences, while intermediate result caching ensures that only affected segments of a pipeline are recomputed during iterative adjustments.
The platform supports a broad range of capabilities, including geospatial modeling through GPS integration, high-dynamic-range panorama generation, and the creation of Gaussian splat models. It also incorporates machine learning tools for depth estimation and language-based image segmentation, alongside mesh optimization features for refining geometry and texture mapping.
Interoperability is facilitated through data exchange protocols that connect reconstruction pipelines with external 3D modeling software. The system is built upon the AliceVision computer vision framework, providing a modular architecture that supports custom plugin development and hardware-accelerated processing.