Are there an original videos in the data set?

[youngstu]

Are there an original videos in the data set, so that 3D pose can be extracted through dynamic capture tool. Thanks.

[youngstu]

DanceRevolution is superior to AI Chreographer in Chinese songs.

AI Chreographer is tested, and the effect is poor in my collected audios such as Chinese songs. Maybe AIST++ data may be the reason for the distribution of training sets.

Therefore, if that there are original videos, it can make a 3D dataset using some tool.

[youngstu]

There are some tools for video inference in human body pose and shape estimation. https://github.com/mkocabas/VIBE/tree/master https://github.com/Arthur151/ROMP

[stonyhu]

@youngstu Thank you for your interest in our work. Yes, we have the original video data but there might be some legal or copyright issues if we publicly release it. You can contact me via the email.

[youngstu]

@youngstu Thank you for your interest in our work. Yes, we have the original video data but there might be some legal or copyright issues if we publicly release it. You can contact me via the email.

Thank you. I've sent you an email.