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.

Joint 3D Face Reconstruction

124 pointsby tonylemesmerabout 7 years ago

11 comments

superbatfishabout 7 years ago
The shortened HN title here is nonsensical.<p>In this context, &quot;joint&quot; means &quot;together&quot; or &quot;at the same time&quot;. The work&#x27;s title, &quot;Joint 3D Face Reconstruction and Dense Alignment&quot;, essentially means &quot;Face Reconstruction with simultaneous Dense Alignment&quot;. The HN title should mention both parts, or remove the word &quot;joint&quot;.
评论 #16981248 未加载
mlbossabout 7 years ago
University of Basel has some nice project for 3d Modeling. They also have a scala project for 3d face model construction using Gaussian Processes. All the recent 3d modeling papers use Basel Face Model.<p><a href="https:&#x2F;&#x2F;www.futurelearn.com&#x2F;courses&#x2F;statistical-shape-modelling&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.futurelearn.com&#x2F;courses&#x2F;statistical-shape-modell...</a><p><a href="http:&#x2F;&#x2F;gravis.dmi.unibas.ch&#x2F;PMM&#x2F;" rel="nofollow">http:&#x2F;&#x2F;gravis.dmi.unibas.ch&#x2F;PMM&#x2F;</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;unibas-gravis&#x2F;scalismo-faces" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;unibas-gravis&#x2F;scalismo-faces</a>
pathartlabout 7 years ago
New meme? <a href="https:&#x2F;&#x2F;github.com&#x2F;YadiraF&#x2F;PRNet&#x2F;raw&#x2F;master&#x2F;Docs&#x2F;images&#x2F;reconstruct.jpg" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;YadiraF&#x2F;PRNet&#x2F;raw&#x2F;master&#x2F;Docs&#x2F;images&#x2F;reco...</a>
matte_blackabout 7 years ago
I just realized what this would be great for: Avatars in VR games. Snap a photo or video of your face and have it put straight into your character complete with animations. Excellent.
评论 #16982104 未加载
评论 #16981637 未加载
kpencabout 7 years ago
Wonder why it&#x27;s written in Python 2.7 and not 3?
评论 #16979581 未加载
tostitos1979about 7 years ago
Nice project! I&#x27;ve been dabbling in DL for about a year (skimmed Stanford CNN course, Silver&#x27;s RNN course, Andrew Ng&#x27;s old ML course, etc.). While I can recreate basic stuff like MNIST, I don&#x27;t feel like I can attack a problem like Pose estimation yet. How long does it take? Is it about diving deep into a single problem? Is it worth doing a nanodegree to shore up gaps?
athenotabout 7 years ago
I wonder if this can be extended for the whole body, so as to produce a 3D scan of the skin, and measure the evolution of moles and skin issues.
评论 #16981780 未加载
debtabout 7 years ago
Only white people used as examples. Might be useful to literally diversify your dataset.
评论 #16980448 未加载
评论 #16979807 未加载
评论 #16979750 未加载
评论 #16982376 未加载
codetrotterabout 7 years ago
Good READMEs are important and this is a great example of a good README. The gif at the top alone instantly tells you a lot about what the project is about.
ddtaylorabout 7 years ago
Looking through the repo, anyone help me find where they put the vertices data that maps to image set?
bsenftnerabout 7 years ago
Have at it, deep fake geeks...