Unwanted behaviour when using white background once normal loss starts
RobinRenggli opened this issue · 2 comments
I'm training on a set of images that have been preprocessed by applying a segmentation mask, i.e. the background is white.
Training works well up until iteration 7000, which is until the normal loss kicks in:
However, after I start applying the normal loss, I get unwanted gaussians, such as seen here:
Which eventually grow to fill the entire background:
Is there any way to fix this behavior with the current implementation?
I did some more experimentation and noticed this only occurs once densification and pruning stops. I'm guessing that since there is no loss to discourage gaussians from covering the background, if they have the same color, this can occur.
Feel free to close the issue, I'd be interested on your thoughts though.
Just saw this was answered in Issue 22