COLMAP is a general-purpose Structure-from-Motion (SfM) and Multi-View Stereo (MVS) pipeline with a graphical and command-line interface. It offers a wide range of features for reconstruction of ordered and unordered image collections. The software is licensed under the new BSD license. If you use this project for your research, please cite:
The latest source code is available at https://github.com/colmap/colmap. COLMAP builds on top of existing works and when using specific algorithms within COLMAP, please also cite the original authors, as specified in the source code, and consider citing relevant third-party dependencies (most notably ceres-solver, poselib, sift-gpu, vlfeat).
- Binaries for Windows and other resources can be downloaded from https://github.com/colmap/colmap/releases.
- Binaries for Linux/Unix/BSD are available at https://repology.org/metapackage/colmap/versions.
- Pre-built Docker images are available at https://hub.docker.com/r/colmap/colmap.
- Conda packages are available at https://anaconda.org/conda-forge/colmap and
can be installed with
conda install colmap - Python bindings are available at https://pypi.org/project/pycolmap.
- To build from source, please see https://colmap.github.io/install.html.
The documentation is available at https://colmap.github.io/.
Please, use GitHub Discussions at https://github.com/colmap/colmap/discussions for questions and the GitHub issue tracker at https://github.com/colmap/colmap for bug reports, feature requests/additions, etc.
COLMAP was originally written by Johannes Schönberger with funding provided by his PhD advisors Jan-Michael Frahm and Marc Pollefeys. The team of core project maintainers currently includes Johannes Schönberger, Paul-Edouard Sarlin, and Shaohui Liu.
The Python bindings in PyCOLMAP were originally added by Mihai Dusmanu, Philipp Lindenberger, and Paul-Edouard Sarlin.
The project has also benefitted from countless community contributions, including bug fixes, improvements, new features, third-party tooling, and community support (special credits to Torsten Sattler).