COLMAP - Structure-From-Motion and Multi-View Stereo
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 GNU General Public License. If you use this project for your research, please cite the papers: PDF / Bibtex / Video and PDF / Bibtex / Video.
Documentation and Support
New releases will be announced via the Google Group. Simply subscribe to this thread to receive notifications for major new releases.
Current (Version 2.1)
- Vocabulary tree 64K
(for small-scale image collections)
- Vocabulary tree 256K
(for medium-scale image collections)
- Vocabulary tree 1M
(for large-scale image collections)
WARNING: These trees are trained for the GPU-based SIFT implementation and are not compatible with the CPU-based SIFT implementation. Expect significantly degraded efficiency and precision when using these trees with the CPU-based SIFT implementation.
This is an introductory video tutorial to quickly get started with COLMAP. More information can be found in the documentation.