COLMAP is a general-purpose, end-to-end image-based 3D reconstruction pipeline (i.e., Structure-from-Motion (SfM) and Multi-View Stereo (MVS)) with a graphical and command-line interface. It offers a wide range of features for reconstruction of ordered and unordered image collections. The software runs under Windows, Linux and Mac on regular desktop computers or compute servers/clusters. COLMAP is licensed under the BSD License and, if you use this project for your research, please cite the papers: Paper / Bibtex / Video and Paper / Bibtex / Video.
Documentation and Support
The source code is available on GitHub and the documentation is available at colmap.github.io. Please, use the Google Group (firstname.lastname@example.org) for questions and the GitHub issue tracker for bug reports, feature requests/additions, etc.
New releases will be announced via the Google Group. Simply subscribe to this thread to receive notifications for major new releases.
Notice: For full dense reconstruction support, download the binaries with CUDA, which require a NVidia GPU.
→ Pre-Release Version (recommended)
This is the development with all the latest improvements. In general, it is recommended to use the pre-release version, since it is more frequently updated with new fixes than the release version.
This is the stable version, which is typically released after major new features have been added and tested for longer periods of time.
- Vocabulary tree with 32K visual words
(for small-scale image collections, i.e. 100s to 1,000s of images)
- Vocabulary tree with 256K visual words
(for medium-scale image collections, i.e. 1,000s to 10,000s of images)
- Vocabulary tree with 1M visual words
(for large-scale image collections, i.e. 10,000s - 100,000s of images)
The easiest way to build a model from images is to use the automatic reconstruction tool. For more fine-grain control, this is an introductory video tutorial to quickly get started with COLMAP. More information can be found in the documentation.