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.

ML turns video of a 360° turn into 3D model of a person

96 pointsby mikeyandersonabout 7 years ago

10 comments

symisc_develabout 7 years ago
Link to the paper: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1803.04758" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1803.04758</a>
评论 #16839062 未加载
llaoabout 7 years ago
Oh how I hate marketing speech.<p>First of all, the title should include &quot;video of a predefined 360° turn&quot;.<p>And then they say something along the lines of &quot;average accuracy of about 5mm&quot; for joining the constructed modeled joints to their model, while you see the body wobbling around happily.<p>This is an impressive demo, but gah!
评论 #16839738 未加载
nitrogenabout 7 years ago
Structure from motion is an existing technique. What is the contribution of ML in this case (it seems like joint positioning maybe?)?<p><a href="https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Structure_from_motion" rel="nofollow">https:&#x2F;&#x2F;en.m.wikipedia.org&#x2F;wiki&#x2F;Structure_from_motion</a>
评论 #16839404 未加载
评论 #16838235 未加载
raghavkhannaabout 7 years ago
How is this ML? They use a CNN for foreground segmentation, a minor step in their pipeline. But the major contribution seems to be putting the silhouettes in a common reference frame. I sincerely hope sciencemag isn’t putting ML in the title purely to jump on the bandwagon.
评论 #16840222 未加载
评论 #16839493 未加载
egypturnashabout 7 years ago
As an artist, my first thought is <i>I wonder what happens if you try giving this a series of drawings</i>.
评论 #16839151 未加载
mtgxabout 7 years ago
This is what should give you pause before using face authentication technology for anything.
评论 #16838398 未加载
make3about 7 years ago
I wonder if will see a future soon where a director can fully edit the positions and physical actions of the actors at post production.<p>basically, the whole scenes will be transferred to believable 3d models seemlessly, and you can reanimate parts of everything. I feel like that&#x27;s doing to happen for sure, for big Hollywood productions at least (like the Marvel stuff)
评论 #16841006 未加载
interfixusabout 7 years ago
It seems determined to put visible toes on everybody, no matter that they&#x27;re wearing socks.<p>Is this a bug or a feature?
评论 #16838977 未加载
codetrotterabout 7 years ago
This is awesome. I wish someone will implement this as a piece of open source software. Imagine the potential!
评论 #16838799 未加载
mericabout 7 years ago
Could be used for VR phone calls between long distance couples.