datascience-projects icon indicating copy to clipboard operation
datascience-projects copied to clipboard

Why use nearest neighbor to match two histograms in neural style transfer with histogram loss.

Open baldFemale opened this issue 6 years ago • 1 comments

It seems that nearest neighbor brings more fluctuation. Did you try other methods such as bilinear interpolation to match the histograms?

baldFemale avatar Mar 09 '19 04:03 baldFemale

Hi!

I haven't tried other methods, but I was having trouble making the histogram matching work well; alternative methods definitely make sense to experiment with.

gabrieltseng avatar Mar 27 '19 14:03 gabrieltseng