Thanks for the amazing research. I had a few questions, so I left questions.
The questions are:
Is motion_filter.py:69 correct at the beginning of the correlation lookup code?
I wonder why the range of i and j is defined up to rd+1 in the nested for loop of correlation_kernels.cu. This will make the neighborhood grid asymmetric. Any special reason?
Since I am not familiar with CUDA, I am reading the code while trying to understand the flow of variables with my eyes. If I run the kernel for pyramid level 0 of the correlation volume in lines 52 to 65 of correlation_kernels.cu, dx=dy=0, so only the last if statement actually works as true?
Thanks for the amazing research. I had a few questions, so I left questions.
The questions are:
i
andj
is defined up tord+1
in the nested for loop of correlation_kernels.cu. This will make the neighborhood grid asymmetric. Any special reason?Thanks in advance for your reply.