Informatics Seminar (Perspective in Informatics 4B) 2010 - 2011
July 22
(Thu),
16:00 - 18:00
(Note: Irregular slot. No talks on July 23)
- Place:
Lecture Hall 1, Faculty of Engineering Bldg. No.10, Main Campus
First Talk: 16:00 - 17:00
- Title:
3D face tracking including non verbal expressions*
- Speaker:
Andre Gagalowicz (INRIA Paris-Rocquencourt)
- Abstract:
We propose a new technique for 3D face tracking in video
sequences, which works without markers and once initialized, doesn't
require any further interaction. A specific geometric model of the face
(in a neutral position, for example) is used as input as well as a
realistic face animation model. The algorithm includes a new method for
precise face expression tracking in a video sequence which uses this
hierarchical animation system built over a morphable polygonal 3D face
model. Its low-level animation mechanism is based upon MPEG-4
specification which is implemented via local point-driven mesh
deformations adaptive to the face geometry. The set of MPEG-4 animation
parameters is in its turn controlled by a higher-level system based upon
facial muscles structure. That allows us to perform precise tracking of
complicated facial expressions as well as to produce face-to-face
retargeting by transmitting the expression parameters to the different
faces.
Second Talk: 17:00 - 18:00
- Title:
Free-form Surface Tracking Using Multiple Cameras
- Speaker:
Edmond Boyer (Grenoble Universities/INRIA Rhone-Alpes)
- Abstract:
Recovering information on the motion of evolving shapes using
visual cues has been a subject of interest since the 19th century. An
interesting and seminal example is the work of Muybridge on the horse
gallop in 1878. Later, in the 20th century, motion capture systems were
proposed and widely used to recover motion information using visual
markers at sparse locations on shapes. The evolution of image
acquisition systems and of the associated 3D modeling tools make it
possible nowadays to consider dense, instead of sparse, motion
information of arbitrary moving shapes and without the need for markers.
In this talk, I will focus on how to capture such dense motion
information using multiple cameras and I will present recent works
conducted at the INRIA Grenoble and the university of Munich on
surface tracking.
Kyoto University
> Graduate School of Informatics
> International Courses
> Informatics Seminar