Search
Cart
Sign in
  • offerCustomer zone
  • offerYour orders
  • offerEdit account

  • offerAdd project
  • offerLiked projects
  • offerView your artist profile

  • Dark mode

We care about your privacy

We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. The consent is voluntary. You can withdraw it at any time or renew it in Cookie settings on the home page. Withdrawal of your consent does not affect the lawfulness of processing performed before the withdrawal. Privacy Protection Policy
Accept all
Accept selection
Reject all

Total Moving Face Reconstruction

Youtube 2014-09-08 11:32 article  > All

Scientists create 3d models of human faces based on youtube clips.

Supasorn Suwajanakorn, Ira Kemelmacher-Shlizerman, Steven M. Seitz target videos taken under uncontrolled and uncalibrated imaging conditions, such as youtube videos of celebrities. In the heart of this work is a new dense 3D flow estimation method coupled with shape from shading. Unlike related works scientisits do not assume availability of a blend shape model, nor require the person to participate in a training/capturing process. Instead they leverage the large amounts of photos that are available per individual in personal or internet photo collections.

Below you can see the results for a variety of video sequences that include various lighting conditions, head poses, and facial expressions. This video was made for European Conference on Computer Vision (ECCV 2014) which is held on September 6, 2014 in Zurich (Switzerland).

More about tis topic here.

 
Author: Youtube Editor: Michał Franczak
Tags: r&d TotalMovingFaceReconstruction eccv research
You may also like...
Evermotion: More Than an Asset Library

Evermotion: More Than an Asset Library

How Evermotion became a full-scale production partner for archviz, automotive and synthetic data.
×

LEAVE A COMMENT

You need to be logged in to leave a comment. Don't have account? Register now.