search

karfly / learnable-triangulation-pytorch

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

Adding more joints #134

Open BoYuanVisionary opened 3 years ago

BoYuanVisionary commented 3 years ago

Hi, thanks for your great work.

I am trying to train a model which supports the detection of more joints. So could you share more details about how to preprocess the original human3.6m dataset in this case? Especially, how to complete Step 5 in the Human3.6M preprocessing scripts?

shrubb commented 3 years ago

Hi, we don't know. Better ask the original authors. By the way, Karim extracted camera parameters (but not keypoints).

anas-zafar commented 1 year ago

@BoYuanVisionary were you able to do it?