Testing accuracy gap

[wyf0912]

Thanks for your great work!

Did you meet the problem that the testing accuracy is much lower than the training one?
My reproduced test PSNR is only 19.75 (25.34 in the paper) while the training PSNR is the same as the paper.

I repeated the experiment many times but the problem always exists.

Looking for your reply.

[inspirelt]

Hi, please follow

Scaffold-GS/arguments/__init__.py

Line 73 in 3a2cc33

# In the Bungeenerf dataset, we propose to set the following three parameters to True,

to set the dist-related parameters. We will update the inconvenient configuration system as soon as possible.

[wyf0912]

Thanks for your reply. I solved the problem by updating the CUDA.