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

A question about testing 3DGS on human dataset #76

Open
zzg-zzg opened this issue Dec 25, 2024 · 1 comment
Open

A question about testing 3DGS on human dataset #76

zzg-zzg opened this issue Dec 25, 2024 · 1 comment

Comments

@zzg-zzg
Copy link

zzg-zzg commented Dec 25, 2024

Hello, thank you for your contributions to the open-source community. I recently wanted to test human body data on 3DGS, but COLMAP is not working properly.
I noticed the code you shared at this link. This code has been very helpful to me.2
I have a small question: if the internal and external parameters are known but there is no sparse point cloud(from sfm), is the initialization of 3DGS random?

@ShunyuanZheng
Copy link
Collaborator

In such a case, you can initialize from randomly sampled points from SMPL. However, there is no significant difference between the initializations from SMPL or at random.

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