search

Embracing / GFPose

Official implementation for the CVPR2023 paper: "GFPose: Learning 3D Human Pose Prior with Gradient Fields"
Apache License 2.0
123 stars 5 forks source link

Evaluation sampling interval #3

Closed xcharxlie closed 1 year ago

xcharxlie commented 1 year ago

Did you use 640 as the sampling interval in evaluation or you evaluated on the whole test dataset?

Embracing commented 1 year ago

I use 640 as the sampling interval to save the evaluation time. I have also tried evaluating on the whole testset. This generally gives similar or even slightly better performance despite much longer evaluation time.

xcharxlie commented 1 year ago

And most of the results listed in the big table are probabilistic right, unless the ones are stated explicitly.

Embracing commented 1 year ago

In my experience, there is very little variance in the results of each evaluation. The results reported in the paper can be reproduced using the scripts and checkpoints provided in this repo.

xcharxlie commented 1 year ago

Thank you so much! I'm also looking forward to the 3dhp part of code for result comparison.