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

There are many floaters in indoor scenes #800

Open
cici19850 opened this issue May 10, 2024 · 2 comments
Open

There are many floaters in indoor scenes #800

cici19850 opened this issue May 10, 2024 · 2 comments

Comments

@cici19850
Copy link

I used the sample data provided in the paper (tandt_db\db\playroom) to train with very good quality, and there will be no floaters in the air. However, the indoor data I took myself and trained showed that there will be a large amount of black floaters in the air. May I ask how was the tandt_db\db\playroom data captured? What equipment was used for shooting? You can achieve such good training results.
Looking forward to your reply, thank you.

@jaco001
Copy link

jaco001 commented May 10, 2024

Photogrammetry isn't just putting many pictures as you can to software thing ;) Indoor datasets are tricky because you get many one color surfaces and you must know where to put camera to get optimal results.
Here is a nice case study with art gallery https://radiancefields.com/gaussian-splatting-brings-art-exhibitions-online-with-yulei

Take a look at cameras placement - this tell you more.
GL

@cici19850
Copy link
Author

Photogrammetry isn't just putting many pictures as you can to software thing ;) Indoor datasets are tricky because you get many one color surfaces and you must know where to put camera to get optimal results. Here is a nice case study with art gallery https://radiancefields.com/gaussian-splatting-brings-art-exhibitions-online-with-yulei

Take a look at cameras placement - this tell you more. GL

The method you provided me has been of great help to me,Thank you very much

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