OpenSfM is a Structure from Motion library written in Python on top of OpenCV. 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.

Checkout this blog post with more demos

• OpenCV
• Ceres Solver
• Boost Python
• NumPy, SciPy, Networkx, PyYAML, exifread

Use

brew tap homebrew/science
brew install opencv
brew install homebrew/science/ceres-solver
brew install boost-python
sudo pip install -r requirements.txt

Be sure to update your PYTHONPATH to include /usr/local/lib/python2.7/site-packages where OpenCV has been installed:

export PYTHONPATH=/usr/local/lib/python2.7/site-packages:$PYTHONPATH

1. OpenCV - Install by following the steps in the Ubuntu OpenCV installation guide. An alternative instruction tested for Ubuntu 10.04 can be found at OpenCV Docs. OpenCV requires GCC and CMake among other things.

2. Ceres solver - Build Ceres according the documentation. Make sure to read the Linux note, follow the shared library instructions and compile Ceres with the -fPIC option. Install Ceres from the ceres-bin directory after make by:

   sudo make install
   

3. Boost Python - Install through apt-get:

   sudo apt-get install libboost-python-dev
   

4. NumPy, networkx, PyYaml, exifread - Install pip and then run the following from the root of the project:

   sudo pip install -r requirements.txt
   

5. SciPy - Install gfortran through apt-get and then install SciPy with:

   sudo apt-get install gfortran
   sudo pip install scipy
   

python setup.py build

An example dataset is available at data/berlin.

1. Put some images in data/DATASET_NAME/images/
2. Put config.yaml in data/DATASET_NAME/config.yaml
3. Go to the root of the project and run bin/run_all data/DATASET_NAME
4. Start an http server from the root with python -m SimpleHTTPServer
5. Browse http://localhost:8000/viewer/reconstruction.html#file=/data/DATASET_NAME/reconstruction.meshed.json.

Things you can do from there:

• Use datasets with more images
• Click twice on an image to see it. Then use arrows to move between images.
• Run bin/mesh data/berlin to build a reconstruction with sparse mesh that will produce smoother transitions from images