How do batch size come into play in the S3IM formulation about s3im-neural-fields HOT 4 CLOSED

Hello haiphamcse

1. We use the final rgb piexl(batch, 3) instead of intermediate rgb points(batch, num_rays, 3) to make a virtual patch. For example, (4096, 3) --> (64, 64, 3).
2. We use 64 x 64 because in original nerf methods(DVGO, TensoRF) use 4096 as default setting. Due to the repeat time in our methods, I think s3im already have enough randomness, so a bigger patch size maybe not that helpful.

from s3im-neural-fields.

What is the right way to use S3IM if the number of rgb pixels is larger than (4096,3). Do we just change the kernel size proportionally?

from s3im-neural-fields.

No need for increasing kernel size. For example, we can keep the virtual patch as a shape like (64, batch_size / 64 / 3, 3)

from s3im-neural-fields.

Thank you for your reply! I understand now

from s3im-neural-fields.