A real-time Visual-Inertial Odometry (VIO) system using 360° equirectangular cameras with IMU integration.

• C++17 or later
• CMake >= 3.14
• OpenCV >= 4.0
• Eigen3 >= 3.3
• Ceres Solver >= 2.0 (included as submodule)
• Pangolin (included as submodule)
• spdlog (included as submodule)

git clone --recursive https://github.com/93won/360_visual_inertial_odometry.git
cd 360_visual_inertial_odometry

./build.sh

The executable will be generated at build/bin/360_vio_example.

The dataset is from the 360VIO benchmark:

📄 Paper: 360VIO: Robust Visual-Inertial Odometry Using 360 Degree Camera

For convenience, we provide pre-parsed datasets ready to use:

🔗 Google Drive: Download Dataset

cd build
./bin/360_vio_example /path/to/dataset/seq1_vio/

./bin/360_vio_example /home/user/data/360/seq1_vio/

This project is released under the MIT License. See LICENSE for details.