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.

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

straight longhair has bad results #14

Open
doublexxking opened this issue Aug 13, 2023 · 4 comments
Open

straight longhair has bad results #14

doublexxking opened this issue Aug 13, 2023 · 4 comments

Comments

@doublexxking
Copy link

doublexxking commented Aug 13, 2023

As title mentioned, I test straight longhair, the output always is curly hair no matter what the parameter is. Face shape and expression are also not good enough.
Input:
Screenshot from 2023-08-13 17-31-26
NPHM outputs:
Screenshot from 2023-08-13 17-32-34

Additionally, I find that NPHM cannot deal with long bangs.
Do you have some suggestions to handle this kind of situation?

I upload the test scan ply if you need it to check.
scan.zip

@Zvyozdo4ka
Copy link

@doublexxking, Could you explain to me, please, how to give point cloud as input and get a mesh?

@Zvyozdo4ka
Copy link

@doublexxking could you at least say which function did you use, or did you write this script for getting mesh based on point cloud, from scratch?

@Zvyozdo4ka
Copy link

@doublexxking how did you get point cloud? from scanner?

@Zvyozdo4ka
Copy link

Even though i had my own flame and good point cloud, registered and transformed to be in same coordinate system as flame, the result of NPHM does not resemble identity at all. I guess network works only with trained data:

image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants