Hello! Really impressive work! Already starred!
I have 3 questions regarding implementation details.
- For a UNet structure, do you replace all the convolution blocks with RepNR blocks?
- Is the CSA^k representing the noise generator, or does the input F_k already transformed by the noise? Quoting from the paper, "CSA focuses on adjusting the distribution of input features." What purpose does CSA serve?
- Given that the log of system gain is linear with log of the variance of noise, how do we get the noise parameters with 3 paired data? Could you please give me some intuition, or something to read about?
Thanks again for your work!
Hello! Really impressive work! Already starred!
I have 3 questions regarding implementation details.
Thanks again for your work!