How to get gt smpl parameters in arbitrary person data sets

hongsukchoi / Pose2Mesh_RELEASE

Official Pytorch implementation of "Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose", ECCV 2020

MIT License

677 stars 69 forks source link

How to get gt smpl parameters in arbitrary person data sets #2

Open FWC13163296500 opened 3 years ago

FWC13163296500 commented 3 years ago

Hi, @hongsukchoi. superb work and thanks for sharing! I would like to ask how to generate gt smpl parameters on my data set? How to label smpl parameters for two-dimensional images.

hongsukchoi commented 3 years ago

Hi @FWC13163296500, thanks for your interest. As I wrote in the supplement material, the pseudo-groundtruth SMPL parameters are obtained using SMPLify-X. You can check this repository https://github.com/vchoutas/smplify-x to get SMPL parameters on your own dataset. You will need groundtruth 2D annotation for accurate SMPL parameters.