hbb1 opened this issue 10 months ago · 5 comments
If a filter is small enough, we are able to approximate a pixel using a point, so as to achieving high accuracy. However, if the filter is too small, gradient can not be well received. So Here is a trade-off.
We assume the initial scale per-point is small enough, so the low pass filter dominate the training at the beginning.
I empirically set R = $\sqrt{2}/2$.
clase as completed.