Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Differentiable Dithering

peterstefek.me

Post reply on HN
Print view View original

21–30 of 51 posts

Re: Differentiable Dithering

#21

Post by formerly_proven »

bufferoverflow wrote: post #20

What are the applications for dithering these days? I understand it was needed when we had 4 or 16 or 256 color limits. But now we have 8-bit/channel displays, and 10-bit is becoming popular.

Eight and ten bits are the full range of the image, but dark scenes only use a fraction of the range and often suffer from banding (and comically bad compression artifacts on certain popular streaming services). Clean, slight gradients as a backdrop often only cover a small distance in RGB, so again, very low resolution and banding is the result.

Dithering is vital. Just like dithering is vital for audio, even at 24 bits.

Also keep in mind that the "10 bit" you speak of is implemented by dithering on an 8 bit panel in almost every display. Similarly many cheaper 8 bit displays are actually 6 bit with dithering. Additionally, 10 bit is a very rare output format [1] and rarely used by applications apart from the handful of HDR games; even for content creation applications 10 bit support is uncommon, and it actually being utilized even less common.

[1] Just because everything is output and composited in 8 bit, doesn't mean 10 bit display output is entirely for naught. If you are using hardware gamma correction, which you are when you use tools like flux/redshift/... or most ICC display profiles, then 10 bit scanout of an 8 bit framebuffer still makes sense.

Re: Differentiable Dithering

#23

Post by sinity »

formerly_proven wrote: post #21
bufferoverflow wrote: post #20

What are the applications for dithering these days? I understand it was needed when we had 4 or 16 or 256 color limits. But now we have 8-bit/channel displays, and 10-bit is becoming popular.

Eight and ten bits are the full range of the image, but dark scenes only use a fraction of the range and often suffer from banding (and comically bad compression artifacts on certain popular streaming services). Clean, slight gradients as a backdrop often only cover a small distance in RGB, so again, very low resolution and banding is the result. Dithering is vital. Just like dithering is vital for audio, even at 24…

Yeah, since the day I noticed it on one YT video I can't unsee it in every dark one. I didn't even learn why it's so bad for a long time.

Horrible huge squares/rectangles of slightly different black all over the place.

Re: Differentiable Dithering

#25

Post by s1mon »

bufferoverflow wrote: post #20

What are the applications for dithering these days? I understand it was needed when we had 4 or 16 or 256 color limits. But now we have 8-bit/channel displays, and 10-bit is becoming popular.

There are still plenty of 1-bit displays in the world. Consumer electronics with small OLEDs, and various low-power signage have low bit depth. Just because our modern phones and laptops have high bit depth doesn’t mean that dithering goes away.

Re: Differentiable Dithering

#28

Post by underanalyzer »

SimplyUnknown wrote: post #12

Looks cool! Two questions: - Is this approach also learning the palette? It is kind presented as a given here but it is of course very important for a good dithering. - The loss function might work better on spatially downsampled images. The downsampling causes a mix of the image colors making the dithered image look more like the original given a good dithering. This also naturally removes the variance that is now p…

This blew up while I was asleep so I’ll try my best to answer now!

1. Yes the palette is being optimized for as well which is imho what makes it different from a quantization approach 2. That’s a good point. I cite a reference blog post which does use blur in the loss function towards the end of the post. Unfortunately I think pure blur would still produce a noisy image as it would remove variance in the eyes of the loss function but not the final image. I would guess something like the example I give with purple, red, blue pixels would still be a problem for blurred loss

Re: Differentiable Dithering

#29

Post by underanalyzer »

londons_explore wrote: post #2

> A pipedream would be an entirely differentiable image compression pipeline where all the steps can be fine tuned together to optimize a particular image with respect to any differentiable loss function. Neural Image Compression? https://arxiv.org/abs/1908.08988

Yea neural image compression looks pretty neat! The reason I bring up jpeg is because it's so well established and if you come up with a more optimized jpeg (which I'm not really convinced is possible, again a pipedream) you don't have to force people to transition to a new image format. In the end methods like neural style or whatever comes after are probably the better pick but there is a transition period.

Re: Differentiable Dithering

#30

Post by MiroF »

tonic_section wrote: post #17
londons_explore wrote: post #2

> A pipedream would be an entirely differentiable image compression pipeline where all the steps can be fine tuned together to optimize a particular image with respect to any differentiable loss function. Neural Image Compression? https://arxiv.org/abs/1908.08988

Unfortunately you wouldn't have any guarantees on the output of any particular image though, just some reassurances about the expected behaviour over the training set.

> any guarantees on the output of any particular image though

You don't have any guarantees with this non-convex optimization.

I think most of these methods would work OK on out-of-domain data.

Post reply on HN