We dont support a double-sided checkerboard yet, but it is a good idea. For now it just supports a roughly 140deg arc around the checkerboard.

OpenCap does not resolve finger or toe motion. Algorithms that predict SMPL-X or SMPL-H meshes can resolve hands. I'm not aware of any pose estimation models that resolve the toes.

After downloading data, you can load the model into OpenSim to view how the different degrees of freedom move the model. Exact details of joint definitions can be found in the .osim file itself.

Hi Tom A few ideas: 1) visualize your kinematics in opensim and make sure they are good relative to the ground. Is the ground plane oriented correctly? Is the person facing in the +x direction? 2) I would carefully review the formulation and ensure it makes sense for your application (ie that you ar...

Hi - there currently is not a clean way to reprocess data locally with HRNet. You can try with the high resolution openpose settings.

Hi Neha, yes you would need to model the lifted object in the muscle-driven simulation. This forum is for technical questions about OpenCap. We support discussions about research projects through quarterly Restore Center virtual office hours. Keep an eye out here for the application: https://restore...

It should work, but we have not done a validation on lifting specifically.

There is not a blurring feature.

Make sure any checkerboard you use is very flat, and verify the dimensions of the squares.

Errors in translations can be due to inaccurate calibrations. In this case the calibration board has direct sunlight on it, which makes the black-black corners of the board less clear in the image. Two suggestions that I would try in order: 1) Shade the calibration board or face it away from direct ...