Skip to content

COLMAP

  • Software
  • Perception
  • Tool

COLMAP is a general-purpose Structure-from-Motion and Multi-View Stereo pipeline with graphical and command-line interfaces, for reconstructing 3D scenes from image collections.

Made by COLMAP project.

Source on GitHub: github.com/colmap/colmap (opens in a new tab). Facts read at commit c08f96c (opens in a new tab).

Licenses

Code
BSD-3-Clause (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit c08f96c (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Reconstructs ordered and unordered image collections using Structure-from-Motion and Multi-View Stereo.
  • Offers both a graphical interface and a command-line interface.
  • Includes an automatic reconstruction mode that builds models with a single click or command.
  • Provides a global SfM pipeline (GLOMAP) and an image retrieval engine based on a vocabulary tree.
  • Available as Windows and Linux binaries, Docker images, conda packages and Python bindings (pycolmap).
  • Python bindings include CUDA-enabled wheels, and AMD GPUs are supported via HIP/ROCm when building from source.

Written by Robotheca from the project's README (opens in a new tab) at commit c08f96c.

Getting started

Difficulty
Advanced
Hardware it needs, as the project states it
CUDA-enabled wheels exist for NVIDIA GPUs; AMD GPUs are supported via HIP/ROCm when building from source.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
16 Oct 2026 on main
Latest release
4.2.1 (29 Sept 2026)

Checked on GitHub on 16 Oct 2026.

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.