Algorithms for 3D hand pose extraction: a novel implementation

In this work we construct a marker-less 3D hand pose ex- traction solution relying solely on a single RGB video source. We leverage available solutions for state-of-the-art computer vision models, coupled with a custom depth estimation algo- rithm to reconstruct full 3D space data. This system is pack- aged in a Python library capable of real time pose estimation, and is evaluated over two different datasets, one reflecting our intended task and a common academic dataset. The overall results shows limits in the accuracy of the model, measured on average above 10 cm, exceeding the desired precision of a few millimeters, but we acknowledge the relevancy of the results in the larger context of the field, and discuss potential avenues for future work.