hbb1/2d-gaussian-splatting

Question about synthetic dataset

Yubel426 opened this issue · 6 comments

Hi!
When trying to reconstruct the mesh on the synthetic, I noticed a significant presence of black erroneous faces in the output. Have you tested on this dataset before? Should I consider additional hyperparameter adjustments? Any insights or suggestions you could offer for this issue would be greatly appreciated.
1716974362113
1716974419046

hbb1 commented

I need further clarification. Is there floaters outside the objects, i.e., 2D Gaussians that fake the background color?

No additional Gaussian points are generated outside the object (almost none), which I find weird. Below is the corresponding point cloud.
1717035348526

hbb1 commented

I can see some outliers in free space, I am not sure if this causes the issue. Maybe similar to #22 , it can produce gaussians with fake background color when introducing depth-normal consistency.

Thanks, it does seem to be caused by normal consistency.