search

zju3dv / SMAP

[ECCV 2020] SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation
Apache License 2.0
241 stars 37 forks source link

Evaluation #46

Open HuiliCui opened 2 years ago

HuiliCui commented 2 years ago

Thanks for your share. The evaluation metrics used in your paper are very reasonable, and I want to use them to test my own model. Could you share the relevant test codes?

raypine commented 2 years ago

We follow the work of Moon and the official code of MuPoTS-3D dataset.

HuiliCui commented 2 years ago

Thanks for your response. Could you share the code for calculating PCOD, the new metric proposed in the paper?

raypine commented 2 years ago

Sorry for that, I forget we have already provided it. in lib/eval folder

HuiliCui commented 2 years ago

Thanks for your response, it helps a lot. Could you provide details of Panoptic's test set, which frames did you use for each activity? Perhaps you can provide a list.

raypine commented 2 years ago

We adopt uniform sampling and the number of samples is described in the paper.