hongsukchoi / 3DCrowdNet_RELEASE

Official Pytorch implementation of "Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes", CVPR 2022
MIT License
155 stars 15 forks source link

How should I infer my own image? #10

Open Fmin-Zou opened 2 years ago

Fmin-Zou commented 2 years ago

If I want to infer my own image using the demo.py, how can I get the json file of 2D poses result?

hongsukchoi commented 2 years ago

you can get them from hhrnet or openpose repo. Th urls are in the supp. mat.

DarlingHang commented 2 years ago

Can you give some hints on how to convert output from https://github.com/tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation to the json format?