Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch

some problem about the depth value

chjXu opened this issue · 4 comments

chjXu commented

Hi, i use the model to estimate the pose from a 1920x1080 pictures, the depth value of the joint is 230 in camera coordinate. So i want to ask the number of 230 means 230mm in the camera coordinate? And the X and Y is 15, -15.

what's means of the X and Y and depth value?
Thanks.

Hi! X, Y, and Z are 3D joint coordinates in some coordinate space (camera, world, etc.). I believe the units are centimeters.

chjXu commented

This model has a big error, right?

It has reasonable error for monocular 3D pose estimation, you are free to check if it is useful for your needs. It is about 100 mm MPJPE (mean per joint position error) on CMU Panoptic subset.

Hope, it is clear now.