This repository is an official PyTorch implementation of the paper "Learnable Triangulation of Human Pose" (ICCV 2019, oral). Proposed method archives state-of-the-art results in multi-view 3D human pose estimation!
MIT License
1.09k
stars
181
forks
source link
Modified function 'apply_umeyama' in mvn/utils/tred.py #141
I have modified the function 'apply_umeyama' so that it can directly process data from a batch much more efficiently. Here are the codes:
def apply_umeyama(batch_gt, batch_pred, rotation=True, scaling=True):