TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Fractal Interpolation

36 pointsby sirnicolazover 3 years ago

4 comments

etaioinshrdluover 3 years ago
This used to be considered cutting edge for image upscaling. Now, the results look hilariously bad compared to what deep learning upscalers produce.<p>The fractal based methods had a unique painting-like look, and edges remained relatively crisp. This is what it looked like: <a href="https:&#x2F;&#x2F;images-na.ssl-images-amazon.com&#x2F;images&#x2F;G&#x2F;01&#x2F;software&#x2F;detail-page&#x2F;gf-comparison.jpg" rel="nofollow">https:&#x2F;&#x2F;images-na.ssl-images-amazon.com&#x2F;images&#x2F;G&#x2F;01&#x2F;software...</a>
IIAOPSWover 3 years ago
I know I&#x27;m in deep on wikipedia when the random links submitted to HN are already marked as clicked, but I barely recall seeing the article and I definitely didn&#x27;t get to it the first time via HN.
danwillsover 3 years ago
Not sure why they just seemed to stop at IFS as the generating-formula.. I guess finding coefficients for it must be easier? Now (as sibling comment noted) neural-nets have totally owned this type of thing, but I reckon that there would now be ways to make neural-nets produce coefficients for more complex generating formulas, such that the compression ratio could be utterly insane. (Could be like the demoscene &quot;4k intro&quot; of the future?)
评论 #30594362 未加载
bitwaveover 3 years ago
Twitter image coding challenge used this technique a while ago: <a href="https:&#x2F;&#x2F;stackoverflow.com&#x2F;a&#x2F;929360" rel="nofollow">https:&#x2F;&#x2F;stackoverflow.com&#x2F;a&#x2F;929360</a>