search

garyzhao / SemGCN

The Pytorch implementation for "Semantic Graph Convolutional Networks for 3D Human Pose Regression" (CVPR 2019).
https://arxiv.org/abs/1904.03345
Apache License 2.0
460 stars 78 forks source link

Converting Stacked Hourglass keypoints to h36m #28

Closed NielsOsnabrugge closed 3 years ago

NielsOsnabrugge commented 3 years ago

Hi @garyzhao and others. I have been researching different kinds of 3D pose estimation models and really like your work. I do have a few questions.

I currently have a 2D pose estimation (All desired keypoints) using this stacked hourglass model. I am trying to convert it to the desired h36m format using your converter that can be found here. However, even though there is a readme i do not understand how you use the converter for a single (or multiple) 2d keypoint prediction.

Is there anyone that knows how I can convert my 2d predictions to h36m format?

NielsOsnabrugge commented 3 years ago

I fixed the issue by using and editing your converter that i linked above