Skip to content

sfu-rsl/graphite

Repository files navigation

Graphite

Graphite is a GPU-accelerated nonlinear least squares graph optimization framework based on CUDA. It lets you define an optimization problem in terms of unary, binary, and n-ary constraints (e.g. pose graph optimization, bundle adjustment), using data structures defined in C++, which may be useful for applications in robotics and computer vision such as SLAM. Graphite also supports configurable floating point precisions as well as mixed-precision solving.

Warning

Graphite is a work-in-progress research prototype. It may have several bugs, performance issues, and other limitations. The interface and implementation may change over time.

Important Links

License

Graphite is released under the MIT License.

Contributing

If you would like to contribute features, bug fixes, code improvements, documentation, or tests, please open an issue or discussion first. Questions about usage are better suited for discussion.

Projects using Graphite

If your project is using Graphite, please let us know so we can add it to the list!