-
Notifications
You must be signed in to change notification settings - Fork 48
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.
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
Suggestion: Add smoothnet #29
Comments
and the issue of 4d humand that I share the code I did and the results |
Thanks, this looks pretty impressive! I had heard about DarkPose which processes 2D heatmaps to reduce jitter. It is good but older: Do you smooth 2D data, or the triangulated 3D coordinates directly (or the shapes)? |
@davidpagnon , I'm doing it applying directly on the rotation vector and translation. on translation somtimes it gives some odd results, but on the rotation vector it works very well all the times I tested. I use on the final 3d data. thanks for the darkpose link I'll check it out for sure. About applying the smoothnet code, Iam almost sure that I mak a list with 3d vectors and throw that on the smooth script, than I save the result. Its basically it. |
I don't really have any rotations on my output until it is processed by OpenSim, only translations... I'll have a look for sure in a little while! |
it works with translations too. And I was able to get joint translations from open sim, I just didnt know how to use them. I thought they were euler, because there was 3 values, but now, after suffering with another code, seems like opensim would be using rotvec... and scipy con convert it to quaternion or euler, or rotation matrix. that is very important to use on things like armature in blender |
Hello.
I just saw your commit with kalman filter.
and I was thinking that maybe pose2sim could use smoothnet.
I tested it with a project that I'm doing using 4d humans, and it made some really good work. Not all the time, but most of the time the result improved a lot.
If you are interested, here is the link for the smoothnet code
https://github.com/cure-lab/SmoothNet
The text was updated successfully, but these errors were encountered: