TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Low-poly image generation using evolutionary algorithms in Ruby (2023)

118 点作者 thomascountz6 个月前

11 条评论

basjacobs6 个月前
Great write-up, I like the fitness graphs a lot.<p>I did something similar in Julia a while ago in an attempt to learn the language: <a href="https:&#x2F;&#x2F;www.basjacobs.com&#x2F;post&#x2F;2020-11-18-image-triangulation-with-julia&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.basjacobs.com&#x2F;post&#x2F;2020-11-18-image-triangulatio...</a>
评论 #42050032 未加载
steve_gh6 个月前
Camme for the evolutionary stuff (wrote mh PhD on it).<p>Left having leaned that you can switch Tail Call Optimisation on or off in Ruby code.
评论 #42049366 未加载
评论 #42049316 未加载
snats6 个月前
I made some image generation with CLIP and Evolutionary algorithms not so long ago[1] and the results had a bit more life than I was expecting. It is still a contested area of research and you have some cool stuff like CLIPDraw[2] where they use gradient decent to approximate a vector to the embeddings of CLIP.<p>[1] <a href="https:&#x2F;&#x2F;snats.xyz&#x2F;pages&#x2F;articles&#x2F;optimizing_images.html" rel="nofollow">https:&#x2F;&#x2F;snats.xyz&#x2F;pages&#x2F;articles&#x2F;optimizing_images.html</a> [2] <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2106.14843" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2106.14843</a>
antirez6 个月前
Related, but in C language and with a different search algorithm: <a href="https:&#x2F;&#x2F;github.com&#x2F;antirez&#x2F;shapeme">https:&#x2F;&#x2F;github.com&#x2F;antirez&#x2F;shapeme</a>
评论 #42050857 未加载
jeroenvlek6 个月前
Very cool! Like others here I&#x27;ve done something similar about a decade ago [0], but only with inheritance and mutation. This was C++ and Qt.<p>[0] <a href="https:&#x2F;&#x2F;github.com&#x2F;jeroenvlek&#x2F;evopic">https:&#x2F;&#x2F;github.com&#x2F;jeroenvlek&#x2F;evopic</a>
juliushuijnk6 个月前
I tried something related many years ago; to evolve a image format that should be tiny:<p><a href="https:&#x2F;&#x2F;medium.com&#x2F;@JuliusHuijnk&#x2F;experiment-in-evolving-the-smallest-image-file-format-6c689e7ec79e" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@JuliusHuijnk&#x2F;experiment-in-evolving-the-...</a><p>To be honest I haven&#x27;t yet read the original article, since it&#x27;s huge. It seems to aim for something compareable.
评论 #42049597 未加载
评论 #42050508 未加载
jensenbox6 个月前
Where is the scrollbar?
评论 #42050421 未加载
评论 #42051592 未加载
chankstein386 个月前
I did something similar to this once and used a similarity algorithm for fitness. The result was really neat, the output image looked very similar to the input image when you were zoomed out but when you zoomed in it was unrecognizable. It was a really interesting result!
评论 #42054656 未加载
jes6 个月前
John Koza has something like three or four books on Genetic Programming. It&#x27;s all in Lisp and I enjoyed working with different examples from his books. If I ever have enough free time, I&#x27;d like to go back and work with it again for a while.
Traubenfuchs6 个月前
This was cool on 4chan 10 years ago. I remember writing my own implementation using lots of unsafe C#.
评论 #42053594 未加载
virtualritz6 个月前
There seems to be a competition on making blogs as difficult to read as possible lately.<p>A monospaced font with narrow line spacing. 40 years of typesetting tech and 500 years of typography and insights on what makes a text readable thrown out of the window.<p>To get what exactly? Some fake retro charme?<p>I gave up reading after the first three paragraphs.
评论 #42051027 未加载
评论 #42050936 未加载
评论 #42053789 未加载
评论 #42051841 未加载
评论 #42051003 未加载