search

mks0601 / 3DMPPE_ROOTNET_RELEASE

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
MIT License
477 stars 65 forks source link

Where is Human36M/bbox/bbox_human36m_output.json #11

Closed ykamikawa closed 4 years ago

ykamikawa commented 4 years ago

Hi, Thank you for your great works!!

I would like to train this model from scrach. Where can I get bbox_human36m_output.json?

ykamikawa commented 4 years ago

and, I would like to know the difference of root_img and root_viz .

mks0601 commented 4 years ago
  1. You can download at README.
  2. root_img is coordinate, and root_vis is binary value which indicates root is visible or not.
ykamikawa commented 4 years ago
  1. Thank you for your prompt response.
  2. Is root_img coordinate in the original image or the cropped image?
mks0601 commented 4 years ago

Could you specify by the line number and code file name?