FRESH

Hacker News

Home

Show HN: High-Res Neural Cellular Automata

198 points by esychology

by whilenot-dev

2 subcomments

The automata just completely destroys the image if I draw too much over the stabilized image with the brush. 5 horizontal swipes are enough to destroy the kitty, is that to be expected?
EDIT: video here: https://imgur.com/a/ItZGd5X

by WhitneyLand

2 subcomments

At a glance it looks like it could be just iterative texture sampling.
The difference is when creating each pixel, there’s no coordinate to look up, instead it’s using only a set of rules like Conway’s game of life.
But the rules come from a neural network trained on the image, so… it’s kind of memorizing enough information to effectively do the same thing as texture sampling, but using only local information.
I’m sure I’m missing something about how it works or what makes it interesting…

by zcw100

0 subcomment

I've always loved the original work and it's nice to see they're still working on it. I've always wondered if there was a way to connect this back to infrastructure rather than images. Something you could run on a cluster and if portions of it failed it would regenerate the system.
Like a bio inspired Kubernettes.....Bionettes.

by IvanLudvig

0 subcomment

incredible work! I love seeing progress in this field. I've recently built a WebGPU implementation of the original growing neural CAs: https://github.com/IvanLudvig/neural-ca-webgpu

by jekude

1 subcomments

The abstract implies that strictly local updates are a hinderance to high res, however i would have thought there would be an interesting way to get speed up gains from neighbor-only traffic on GPUs CAM-style. am i making that up?

by EstanislaoStan

0 subcomment

Managed to get a stable loop with the worm!

by embedding-shape

2 subcomments

Really interesting demo, nicely done :) Would be fun if switching the "Target Image" when using the second brush mode in the Growing Demo didn't erase/reset the existing canvas, so we could "stamp" new things on top of other images. Small thing perhaps but I got sad when it disappeared when I wanted to merge a kitten on top of the chameleon but couldn't :(

by hidelooktropic

2 subcomments

For the unfamiliar, could someone explain what I'm looking at? The abstract was a little too concrete (heh) for me to follow.

by WithinReason

1 subcomments

You can make the centipede grow longer, which makes sense given how this works. Or grow a 2nd centipede for extra points.

by _menelaus

0 subcomment

Fascinating. A glimpse into the mathematics of life and living tissue. A toy example like this might herald self-healing machines, in the same way that the first perceptrons heralded Fable and nude deepfakes.

by amelius

2 subcomments

Why are the images always generated in the same orientation (upright)? Do the cells have awareness of what is "up"?

by mirekrusin

0 subcomment

So the goal is to evaporate it with minimum number of shots?

by bjourne

0 subcomment

I found your previous work here: https://distill.pub/2020/growing-ca/ For someone (like me) who wants to understand the basics its probably better. It's very well written.

by moralestapia

2 subcomments

@esychology this is phenomenal work, thank you so much for sharing it. I am working in a similar thing and might reach out about it soon.
Also, what's going on? Why would the community flag and kill this comment[1], from the creator itself. If you're jealous of what the guy built, take it elsewhere. HN will implode with that attitude.
1: https://news.ycombinator.com/item?id=48571171

by hyqzz8

0 subcomment

[dead]