Hi, I have two questions regarding the implementation details.
Fig. 2. shows the R and I components decomposed by your network. But how do you output an enhanced image? Do you use another sub-network to enhance the illumination map?
For the histogram equalization loss, can you give some ideas on how to implement that?
Hi, I have two questions regarding the implementation details.
Fig. 2. shows the R and I components decomposed by your network. But how do you output an enhanced image? Do you use another sub-network to enhance the illumination map?
For the histogram equalization loss, can you give some ideas on how to implement that?
Thank you.