Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

No need to predict 3d pose for every past frames? #45

Open
sylyt62 opened this issue Aug 3, 2022 · 0 comments
Open

No need to predict 3d pose for every past frames? #45

sylyt62 opened this issue Aug 3, 2022 · 0 comments

Comments

@sylyt62
Copy link

sylyt62 commented Aug 3, 2022

Hey I have a question here, since you just take the last 3d pose from joint3D sequence (and indeed it is necessary for real-time application to do so):

videopose/tools/demo.py

Line 40 in 6da0415

joint3D_item = joint3D[-1] #(17, 3)

is it actually meaningless to predict every history frames?

It will be much time efficient if you could only forward the newest 2d pose every time. Is it right?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@sylyt62