ExUtumno
Joined 10 years ago
Karma
530
Submissions
28
Member since
Aug 10
https://github.com/mxgmn
View on Hacker NewsRecent submissions
Comment · 4 years ago
Author here, I'll try to answer questions/comments in this post!
Comment · 4 years ago
Thanks for reposting, I don't mind.
Comment · 4 years ago
Thanks! I would have probably never known about Markov algorithms if I were not taught them in 8th grade =)
Comment · 4 years ago
Thank you!
For MarkovJunior, the recent projects that were impactful the most were Imagegram by Guilherme S. Tows [1] and Daniel Ritchie's dissertation [2] about PPLs for procgen. I took quite a different approach from Ritchie's though.
Comment · 10 years ago
At first I thought that my methods don't offer anything new to text generation besides the Markov chain, but several people already proposed ideas that sound sensible, so let me know if you make anything!
Comment · 10 years ago
Most of the examples in the repo have those NxN all one color patches. Or, without (C2) the algorithm would have generated completely empty integrated circuits, or completely grass terrain, which is really boring.
You understood right, it's constraints + probabilities.
Btw, I have different algorithm that satisfies (C2) perfectly, but not (C1): https://github.com/mxgmn/ConvChain
Comment · 10 years ago
There are special approaches to generating music. The best for ratio of quality/complexity that I know of are Markov constraints https://www.youtube.com/watch?v=buXqNqBFd6E and WaveNet. I don't think WFC offers something useful and new for generation of music.
Comment · 10 years ago
In overlapping models we store probabilities for NxN blocks of colors/tiles. In non-overlapping models we store probabilities for individual colors/tiles.
Comment · 10 years ago
Yes, (C1) is a constraint problem. But we also want to satisfy (C2) as close as possible, otherwise we could have just colored some outputs in a single color.
Comment · 10 years ago
A very good question! The opposite of it is also important, can we follow some heuristics while creating tilesets to minimize contradiction rates, but not making tilesets easy? I don't know. If someone knows please tell me.
Comment · 10 years ago
We need to interpret those coefficients somehow. Real coefficients can be interpreted as mixing of colors, but for complex ones I don't see a good interpretation.
Comment · 10 years ago
I'm not experienced with the license law, but people told me that it's better to have license text in source files themselves, because I have samples in the repo that I have no idea who has rights for.
The license is MIT.
Comment · 10 years ago
I wonder too =). But it'll run like forever on a high res image. For high res image you want to use something like texture synthesis, see my reply to fitzwatermellow for more.
Comment · 10 years ago
If you use overlapping model (there are 2 models in the repo) with 1xN patterns, it would be a the same as (N-1)th order Markov chain.