colmap: a general-purpose Structure-from-Motion and Multi-View Stereo pipeline for 3D reconstruction

What it solves

COLMAP is designed to reconstruct 3D structures from a collection of 2D images. It addresses the challenge of turning a set of ordered or unordered image collections into a 3D model, providing a complete pipeline for Structure-from-Motion (SfM) and Multi-View Stereo (MVS).

How it works

The software provides a general-purpose pipeline that combines Structure-from-Motion (SfM) and Multi-View Stereo (MVS) algorithms. It allows users to process image collections to build 3D models, featuring an "automatic reconstruction" mode for simplified workflows. It is available as a command-line interface (CLI) and a graphical user interface (GUI).

Who it’s for

Researchers and developers working in computer vision, 3D reconstruction, and spatial mapping, as well as anyone needing to turn image sets into 3D models.

Highlights

• Comprehensive Pipeline: Combines both SfM and MVS in one tool.
• Flexible Input: Handles both ordered and unordered image collections.
• Crosspatform Support: Available for Windows, Linux/Unix/BSD, and via Docker and Conda.
• Python Bindings: Offers pycolmap for integration into Python workflows.
• Automatic Reconstruction: One-click/command reconstruction for ease of use.