search

fabro66 / GAST-Net-3DPoseEstimation

A Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video (GAST-Net)
MIT License
313 stars 70 forks source link

Unknown person number #17

Closed guerrifrancesco closed 3 years ago

guerrifrancesco commented 3 years ago

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

fabro66 commented 3 years ago

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.