Insufficient hash resolution harming performance about torch-ngp HOT 6 CLOSED

@xmk2222 You are right, this is a difference from instant-ngp. However, although we assumes the scene is twice larger in length, we also twice the min step size in ray marching here. So it shouldn't affect much as long as bound is the same as aabb_scale.

from torch-ngp.

Thanks for reporting this. According to this line, desired_resolution should be linearly scaled with aabb_scale (bound in this implmentaiton).
Another problem is that we don't have a multi-scale density grid, and exponential ray marching is not supported, which may lead to worse performance too.
However, currently I don't have a dataset large enough to test these changes, could you share the dataset name if it is openly available?

from torch-ngp.

NHR provides a multiview dataset for humans.

from torch-ngp.

@xmk2222 I have added the scaling in 086b15c, but on a naive test with lego (bound=16, scale=10), the results are still blurry. Maybe you could test on your dataset again?

from torch-ngp.

@ashawkey Thanks! That is exactly what I meant. I will test it later.

However, I think there are some differences still:
In instant-ngp, the condition is:

• aabb_scale: 16
• desired_resolution: 32768,
• bounding_box: [-7.5, 8.5];

But in torch-ngp:

• bound: 16
• desired_resolution: 32768 (same as in i-ngp)
• bounding_box: [-16, 16] which is different from the scale of in i-ngp.

The corresponding code in instant-ngp:

https://github.com/NVlabs/instant-ngp/blob/692ce14f4f154c03c5784a944c625da94b08e292/src/testbed_nerf.cu#L2293:L2294

In my trial, the hash encoding has some tolerence in scaling, but maybe it would be better to strictly align with i-ngp, at least in scaling?

from torch-ngp.

As the cascaded density grid has been implemented, I'll close this for now.

from torch-ngp.