search

cure-lab / DeciWatch

[ECCV 2022] Official implementation of the paper "DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation"
Apache License 2.0
177 stars 15 forks source link

Inference on custom videos and multi people tracking #5

Closed CloudedLeopard17 closed 2 years ago

CloudedLeopard17 commented 2 years ago

Hi, Thanks for your great work. I want to do inference on my custom video, how to do it? Also, does it supports multi people tracking?

ailingzengzzz commented 2 years ago

Hi, @CloudedLeopard17, As we discussed in the Quick Demo, we only provide demo visualization based on offline processed detected poses of specific datasets(e.g. AIST++, Human3.6M, 3DPW, and Sub-JHMDB). To visualize on arbitrary given video, please refer to the inference/demo of MMHuman3D. This version does not support multiple person tracking. You may simply use top-down pipelines to first detect and recognize the same person, then use DeciWatch for each person.

CloudedLeopard17 commented 2 years ago

Thanks @ailingzengzzz