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

Remove floaters #57

Open
pierotofy opened this issue Mar 22, 2024 · 5 comments
Open

Remove floaters #57

pierotofy opened this issue Mar 22, 2024 · 5 comments
Labels
enhancement New feature or request

Comments

@pierotofy
Copy link
Owner

pierotofy commented Mar 22, 2024

There should be a way to reduce/filter floaters.

image

These significantly reduce the quality of visualization.

I thought about doing a nearest neighbor search from of the splat means compared to the points in the initial point cloud and filter any splat that is not within X units of an original point. But I don't know if this would work, as certain areas could have no initialization points. If there are better/proven methods I'd like to hear it.

@pierotofy pierotofy added the enhancement New feature or request label Mar 22, 2024
@pfxuan
Copy link
Collaborator

pfxuan commented Mar 22, 2024

This method can give some help. But it’s a little computation heavy.

@pierotofy
Copy link
Owner Author

pierotofy commented Mar 23, 2024

Interesting, it's similar to this one from PDAL: https://pdal.io/en/2.7.0/stages/filters.outlier.html#statistical-method (which can be made to run fast).

@pfxuan
Copy link
Collaborator

pfxuan commented Mar 23, 2024

Good idea. Open3D also has a few similar built-in functions: https://www.open3d.org/docs/latest/tutorial/Advanced/pointcloud_outlier_removal.html

@pierotofy
Copy link
Owner Author

pierotofy commented Mar 25, 2024

I've tried to implement this method in https://github.com/pierotofy/OpenSplat/tree/filter, but although there's some reduction of noise, there's also an increase in other parts (at least in the train dataset) near the object of interest. The validation loss also seems to increase.

@pfxuan
Copy link
Collaborator

pfxuan commented Mar 25, 2024

Perhaps removing floaters could be considered as a post-processing step after the 3DGS model gets fully trained. Additionally, I found enhancing the training code, improving camera pose, and removing blurry image could substantially minimize floating artifacts.

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

No branches or pull requests

2 participants