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.

Photos from Crude Sketches: Nvidia's GauGAN Explained Visually

124 pointsby AdamDKingabout 6 years ago

6 comments

AdamDKingabout 6 years ago
NVIDIA just released the code: <a href="https:&#x2F;&#x2F;github.com&#x2F;nvlabs&#x2F;spade&#x2F;" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nvlabs&#x2F;spade&#x2F;</a>
评论 #19642805 未加载
评论 #19642542 未加载
ggmabout 6 years ago
I find this ... disquieting. I think its fantastic but I also find something about the <i>lack</i> of uncanny valley troubling.<p>I should feel happier about it, but I can&#x27;t stop feeling a bit odd that a sketch can go to photorealistic north of the bad so well now: I expected 5-10 more years for this.
评论 #19643186 未加载
评论 #19641244 未加载
dvasdekisabout 6 years ago
Imagine the impact on moviemaking that this will have within just a few iterations of processing power. Thousands of hours of visual effect artist work in film and TV will soon be abstracted into some high-level commands, transformed by software into moving film. Very exciting.
评论 #19643475 未加载
评论 #19642246 未加载
canada_dryabout 6 years ago
Wow... the effort that went into this article is impressive! Great animations and explanations to decompose what is a pretty complex subject.<p>Nicely done.
Animatsabout 6 years ago
That is one of the best articles I have ever seen on a complex technical subject. A reasonable amount of math, great examples, and animations of the process.<p>If the massively online education people had that kind of quality, maybe people would actually finish the courses.
ebg13about 6 years ago
If you want to see the same thing done 18 years ago without new-age machine learning, read <a href="https:&#x2F;&#x2F;www.mrl.nyu.edu&#x2F;projects&#x2F;image-analogies&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;www.mrl.nyu.edu&#x2F;projects&#x2F;image-analogies&#x2F;index.html</a> IMO the most elegant vision&#x2F;graphics algorithm ever written.<p>Specifically this is the &quot;texture-by-numbers&quot; application. Ex: <a href="https:&#x2F;&#x2F;www.mrl.nyu.edu&#x2F;projects&#x2F;image-analogies&#x2F;potomac.html" rel="nofollow">https:&#x2F;&#x2F;www.mrl.nyu.edu&#x2F;projects&#x2F;image-analogies&#x2F;potomac.htm...</a><p>Every single fancypants application of neural nets in graphics today is a retread of one of the applications of the Image Analogies algorithm.
评论 #19639739 未加载
评论 #19639712 未加载
评论 #19642762 未加载