Hi,
I'd like to use GAST-Net with generic video streams without knowing how many people are in the scene in advance. I need to do this in order to have 3D skeletons of every person depicted in the scene.
Is it possible? Thanks
It is possible to reconstruct multi-people 3D poses from a scene. But the reconstructed accuracy will be subjected to the detected 2D pose. We recommend it for single and two-person scenarios.
Hi, I'd like to use GAST-Net with generic video streams without knowing how many people are in the scene in advance. I need to do this in order to have 3D skeletons of every person depicted in the scene. Is it possible? Thanks