Gradients of the existing bilateral filter layers (normal and PHL)

Describe the bug
The backward operations of the existing bilateral filter layers (normal and PHL) do not calculate the correct derivative of the filter prediction with respect to the filter input. Currently, they use the exact same filter forward function as the backward operation, which is not the correct derivative as shown in here. This issue is related to #1840 and may be partly fixed by pull-request #5757.

As discussed with @wyli we should think about how to treat the existing bilateral filter implementations (normal and PHL). I believe that their forward operations are fast and valid operators which can be valuable for users. However, their provided gradient is not correct I think. The normal bilateral filter implementation could be replaced by the #5757 version in the medium term as their forward operations are almost identical.

To Reproduce
Steps to reproduce the behavior:

1. Install BUILD_MONAI=1 pip install --no-build-isolation git+https://github.com/Project-MONAI/MONAI#egg=monai
2. Run the gradcheck

import torch
from monai.networks.layers import BilateralFilter


tensor_in = (torch.randn(2, 1, 10, 10, 10, dtype=torch.double, requires_grad=True))
filter = BilateralFilter.apply
gradcheck(filter, (tensor_in, 1.1, 0.5), eps=1e-6, atol=1e-5)

Expected behavior
Gradcheck passes.

Current behavior
Gradcheck fails as visible in the screenshot.

Start by running the provided PyTorch gradcheck for BilateralFilter.apply and inspect the existing bilateral filter layer implementation for the normal and PHL variants. Compare the backward behavior with the derivative described in the cited paper and review pull request #5757 for related changes. Done means the relevant gradient checks pass for the existing implementations.