33 / 36
Student corner
Additionally, it can
improve the medical
sector in simulating the
outcomes of plastic
surgeries. For people who
already bought the new
iPhone don’t be afraid
Aaron Jackson thinks that
it’s questionable that this
new tool can trick the 3D
facial scanner which
unlock the phone. You
can get your 3D face
model ready in seconds,
try it out in this link:
http://www.cs.nott.ac.uk/~psxasj/3dme/ .
A new web app is out there, that permit
you to upload a colored image and in a flash,
a 3D model of your face is displayed. In the
University of Nottingham and Kingston a
group of computer scientist have developed a
technology using a Convolution Neural
Network (CNN); it is an aspect of artificial
intelligence that uses machine learning to
provide computers to capability to learn
without being programmed.
The CNN have been trained on a very
big dataset of 3D facial models and 2D
pictures. On top of that it takes good
predictions of the face parts that are not
visible in the image. Actually the website is
demo of the research paper Large Pose 3D
Face Reconstruction from a Single Image via
Direct Volumetric CNN Regression and it’s
going to be presented at the International
Conference on Computer Vision (ICCV)
2017 in Vince. One of the research team
Aaron Jackson said:” Our CNN uses just a
single 2D facial image, and works for
arbitrary facial poses (e.g. front or profile
images) and facial expressions (e.g.
smiling)” this can be helpful in advancing
augmented reality, personalize computer
games and in online shopping such as trying
online accessories like glasses.
3D Selfie? From a single photo why not?- Haya Al-Nuaimi
33