search

zju3dv / neuralbody

Code for "Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans" CVPR 2021 best paper candidate
Other
907 stars 130 forks source link

Help regarding - Pose Estimation on SMPL data / SMPL to COCO conversion #154

Closed Dipankar1997161 closed 11 months ago

Dipankar1997161 commented 11 months ago

Hello @pengsida ,

Hope you are doing well.

With the help of Easymocap, I could generate all the necessary rendering on NeuralBody and some Monocular ones.

My final task is - extracting the smpl key points (which is the original smpl joints) and then performing 2d and 3d pose estimation on the data.

Can you provide some insights on this? Should I directly use SMPL joints for both 2d and 3d pose estimation or convert it into COCO format and then do it? I am okay with both methods but haven't found many reliable sources for the conversion of SMPL to COCO.

Since I generated the smpl from Easymocap, I thought of reaching out to you.

I will wait for your response.

pengsida commented 11 months ago

I am not familiar with this. Please open an issue on the EasyMoCap repo.