The repository that this is forked from 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! This repo aims to extend the capabilites to the CMU dataset
I was wondering when training for the CMU dataset you found what the camera positions of the H36M dataset were?
ie.
Translate x,y,z
Rotate x,y,z
There is useful camera information of the H36M dataset here: https://github.com/karfly/human36m-camera-parameters
but in rotation matrix format and I am having trouble converting it into plain x,y and z coordinates in 3d space.
Hi there
I was wondering when training for the CMU dataset you found what the camera positions of the H36M dataset were? ie. Translate x,y,z Rotate x,y,z
There is useful camera information of the H36M dataset here: https://github.com/karfly/human36m-camera-parameters but in rotation matrix format and I am having trouble converting it into plain x,y and z coordinates in 3d space.
Any help would be great
Thanks