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.

Volume.gl – 3D Model from Single Image

85 pointsby nicdabout 7 years ago

11 comments

VikingCoderabout 7 years ago
Shitty 3D is worse than 2D.<p>Source: I worked really hard to make 3D less shitty, and we failed at it, and went out of business.
评论 #16553661 未加载
Jyaifabout 7 years ago
Needs quite a bit of improvement. With the current quality, I don&#x27;t see any possible application.
评论 #16550518 未加载
paulhilbertabout 7 years ago
Having seen the state-of-the-art in action (<a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1607.00730" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;1607.00730</a>) I find the results pretty disappointing. Is there anything I miss?
评论 #16552091 未加载
pmxabout 7 years ago
This was a gear deal more impressive than I expected! I tried a couple of images and it got the depth very close on one and almost perfect on the other. It&#x27;s weird to be able to change the perspective of an image of a place I know and it be as accurate as it is! Kudos.
评论 #16550379 未加载
评论 #16550401 未加载
blainabout 7 years ago
Uploading my own images seems to be broken in Firefox 58.0.2.
评论 #16553368 未加载
评论 #16550569 未加载
dgarceranabout 7 years ago
wow <a href="https:&#x2F;&#x2F;github.com&#x2F;Volume-GL&#x2F;Pulp-Fiction-ARKit" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Volume-GL&#x2F;Pulp-Fiction-ARKit</a>
splittingTimesabout 7 years ago
Reminds me on disneys research, where you take a single picture of your smile and get a full blown 3D teeth reconstruction.<p><a href="https:&#x2F;&#x2F;www.disneyresearch.com&#x2F;publication&#x2F;model-based-teeth-reconstruction&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.disneyresearch.com&#x2F;publication&#x2F;model-based-teeth...</a>
Tepixabout 7 years ago
Once tech advances a bit further and we can quickly generate good 3d environments from movies, we will have so many great worlds to experience in VR - it will be amazing.
评论 #16550907 未加载
gonogoabout 7 years ago
Is there any library like this that can increase reconstruction accuracy with multiple cameras?
评论 #16552499 未加载
swagasaurus-rexabout 7 years ago
Incredible. I sincerely believe advances in computer vision will be dependent on creating a 3d &#x27;mental model&#x27; of imagery&#x2F;video.<p>What happens when you give it images that fool people? For example the infamous Escher drawings.
moondevabout 7 years ago
<a href="https:&#x2F;&#x2F;airtightinteractive.com&#x2F;demos&#x2F;js&#x2F;ruttetra&#x2F;" rel="nofollow">https:&#x2F;&#x2F;airtightinteractive.com&#x2F;demos&#x2F;js&#x2F;ruttetra&#x2F;</a>