search

Nicholasli1995 / EvoSkeleton

Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"
https://arxiv.org/abs/2006.07778
MIT License
332 stars 44 forks source link

Resulted 2D pose of the mentioned HR-Net on Human 3.6M #26

Closed wbhu closed 3 years ago

wbhu commented 3 years ago

Hi,

Thanks for your great work and code. I noticed that you released the pre-trained model of HR-Net for 2D pose estimator, but we still need the crop step, which may lead to an inconsistent 2D result. Could you please directly provide the estimated 2D pose (it may be in .npy format and shouldn't be too large) from the HR-Net on Human 3.6M? I think it will be very helpful for the community.

Nicholasli1995 commented 3 years ago

Hi,

Thanks for your great work and code. I noticed that you released the pre-trained model of HR-Net for 2D pose estimator, but we still need the crop step, which may lead to an inconsistent 2D result. Could you please directly provide the estimated 2D pose (it may be in .npy format and shouldn't be too large) from the HR-Net on Human 3.6M? I think it will be very helpful for the community.

Hi, thank you for the interest in our work. The 2D pose files have already been released. Please go to https://github.com/Nicholasli1995/EvoSkeleton/blob/master/docs/TRAINING.md and you can download the 2D pose predictions (twoDPose_HRN_train.npy and twoDPose_HRN_test.npy). You can make them smaller by converting to float32 and ignoring unused joints.

wbhu commented 3 years ago

Got it. Thanks very much.