Given the same 5mins render time to both MILA and Rombo.Material and considering that Rombo is sampling GGX distribution that has at least a 30% more to sample, Rombo outperforms MILA.
Here a little better looking image for a shiny plastic material.
On our tests instead MIA can barely deal with more than 256samples before start exhibiting weird sampling patterns at high roughness values.
Here with blurry refractions, for the same render time, we have better result with rombo (left panel) compared to MILA (right panel).
Hola! I’ve been following your site for a while now and finally got
the courage to go ahead and give you a shout out
from Huffman Tx! Just wanted to say keep up the great work!