search

Shimingyi / MotioNet

A deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video [ToG 2020]
https://rubbly.cn/publications/motioNet/
BSD 2-Clause "Simplified" License
554 stars 82 forks source link

about: achieving temporal coherence naturally in paper #19

Closed miss-rain closed 3 years ago

miss-rain commented 3 years ago

Great project!

I read your paper, in the sixth part:CONCLUSION, LIMITATIONS, AND FUTURE WORK:

This is the original text:
Finally, since our system is trained in the space of motions, the inherent smoothness of human motions is learned from the data, achieving temporal coherence naturally.

My question: achieving temporal coherence naturally . Does it mean real-time? The input and output are real-time?

thanks!

Shimingyi commented 3 years ago

Answered by email. Short summary: Temporal coherence doesn't mean real-time performance, it's a metric on the output quality. If we want to extend this method to real-time, an offset would be applied which uses [0, 40] to predict [40, 50] rather than[0, 40] predicts [0, 40] currently.