search

Vegetebird / MHFormer

[CVPR 2022] MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
MIT License
538 stars 85 forks source link

How did you get the Ground Truth in 3D pose? #119

Open AliasChenYi opened 1 week ago

AliasChenYi commented 1 week ago

image How do you obtain the Ground Truth for 3D pose estimation? Is it derived from the model's detection results using 2D Ground Truth for training, or is it the original annotated 3D Ground Truth? Additionally, I noticed that the Human3.6M dataset consists of individual images, while the code you provided is designed for 3D pose estimation regression on videos. Could you please advise on how to handle this situation? I look forward to your response if you have the time.