GAST-Net-3DPoseEstimation
GAST-Net-3DPoseEstimation copied to clipboard
What if there's only half a person in the video
This part convert knees and ankles to hips if knees and ankles are invisible in videos, where I don't think it's very reasonable. https://github.com/fabro66/GAST-Net-3DPoseEstimation/blob/783310d0b26f9ff0b47e5036b7c6b864dfb120ef/tools/preprocess.py#L96
Hi~ sorry for not reply promptly.
If the joints are occluded, the coordinates of the keypoints obtained by the 2D detector will have a large deviation, which will seriously affect the 2D-to-3D reconstruction, so we adopt this preprocessing.
Looking forward to hearing if you have any other better solutions.
Having seen the expose(https://github.com/vchoutas/expose) has solved this problem.
Get it. Thanks for the suggestions.