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

Why is extracted mesh.ply like this in MeshLab #180

Open
Cyberyyc opened this issue Nov 25, 2024 · 3 comments
Open

Why is extracted mesh.ply like this in MeshLab #180

Cyberyyc opened this issue Nov 25, 2024 · 3 comments

Comments

@Cyberyyc
Copy link

Hi!
I used dataset , tandt_db/playroom , provided by 3dgs's author. The trained model is excellent as shown in the following
picture .
1732516500714

However , the extracted mesh.ply by render.py seems terrible when viewed in meshlab. How to solve such problems.
image

Thanks a lot!

@hbb1
Copy link
Owner

hbb1 commented Nov 25, 2024

Increasing depth_trunc may fix this.

@Cyberyyc
Copy link
Author

Increasing depth_trunc may fix this.

Thanks, i'll try it and give you some feedback

@Cyberyyc Cyberyyc reopened this Jan 4, 2025
@Cyberyyc
Copy link
Author

Cyberyyc commented Jan 4, 2025

Increasing depth_trunc may fix this.

Hi! I've tried increasing the depth_trunc . Some mesh.ply can be extracted successfully as following(--depth_trunc 12)

image

However ,some mesh file still seems like this
17c0839cadc8e028c79935282a4ec83

In SIBR it looks like this
78f9bb86a05c652351072ca5d2ea734

And the following are my command line I've used for training and rendering.

python train.py -s tandt_db/tandt/office

python render.py -m output/office -s tandt_db/tandt/office --depth_trunc 12(I also tried 0.8 1 1.5 10 and all of them dont work at all)

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