News for hackers. Stuff that matters.
Re:Differentiable Dithering by 0-_-0 on Wednesday September 16, 2020 @05:52AM (#24491099)
A differentiable error diffusion loss would dither the image with quantisation (like in the post), but then minimise the difference between the blurred dithered image and the blurred original, instead of the dithered image and the original. This would tend to distribute errors so that the average colour in an area is the same in the dithered image as the original, similar to Floyd-Steinberg.

There are no comments on this comment yet.