CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation. (arXiv:2208.00571v2 [cs.CV] UPDATED)

Top-down methods dominate the field of 3D human pose and shape estimation,
because they are decoupled from human detection and allow researchers to focus
on the core problem. However, cropping, their first step, discards the location
information from the very beginning, which makes themselves unable to
accurately predict the global rotation in the original camera coordinate
system. To address this problem, we propose to Carry Location Information in
Full Frames (CLIFF) into this task. Specifically, we feed more holistic
features …

arxiv human information location