OpenSfM is a Structure from Motion library written in Python. The library serves as a processing pipeline for reconstructing camera poses and 3D scenes from multiple images. It consists of basic modules for Structure from Motion (feature detection/matching, minimal solvers) with a focus on building a robust and scalable reconstruction pipeline. It also integrates external sensor (e.g. GPS, accelerometer) measurements for geographical alignment and robustness. A JavaScript viewer is provided to preview the models and debug the pipeline.
OpenSfM is BSD-style licensed, as found in the LICENSE file. See also the Facebook Open Source Terms of Use and Privacy Policy
In sample folder, there are config.yaml and camera_models_overrides.json. The difference from the original repository is this repository can use GPU acceralated feature and matching(feature: SUPERPOINT, DISK, ALIKED, matcher: LIGHTGLUE)
Sample data for 360 degree camera can be found here.
Start reconstruction with this command.
./bin/opensfm_pointcloud data/your_data_dir
After reconstruction, you will see reconstruction.json. You can visualize with opensfm viewer.
python3 viewer/server.py -d data/your_data_dir
You can use reconstruction.json and images for 360 gaussian splatting.