Campus Event Calendar

Event Entry

What and Who

3D Image Analysis and Synthesis

Prof. Dr. Hans-Peter Seidel
AG 1, AG 2, AG 3, AG 4, AG 5  
AG Audience

Date, Time and Location

Thursday, 21 April 2005
-- Not specified --


This abstract is available as PDF file from
  including the figures that had to be omitted from
  this text-only version.

Computers are more and more used to model, simulate and render parts
of the real world or an imaginary world, and due to the importance of
visual information for humans, computer graphics will play an
increasingly important role in the future. Furthermore, new and
emerging technologies such as multimedia, digital television,
telecommunication and telepresence, virtual reality, or 3D-internet
heavily draw upon computer graphics. Typical for the field is the
coincidence of very large data sets with the demand for fast
(if possible interactive) high quality visual display of the
results. Furthermore, the user should be able to interact with
the environment in a natural and intuitive way.

In order to address the challenges mentioned above, a new and more
integrated scientific view of computer graphics is required. In
contrast to the classical approach to computer graphics which takes as
input a scene model consisting of a set of light sources, a set of
objects (specified by their shape and material properties), and a
camera and uses simulation to compute an image, we therefore like to
take the more integrated view of 3D Image Analysis and Synthesis for
our research, and consider the whole pipeline from data acquisition
over processing to rendering in our work. In our opinion, this point
of view is necessary in order to exploit the capabilities and
perspectives of modern hardware, both on the input (sensors, digital
imaging) and output (graphics hardware) side. According to this point
of view, one of the key research challenges then is the development of
good models and modeling tools to efficiently handle the huge amount
of data during the acquisition process and to facilitate further
processing and rendering.

An example for this approach is the acquisition, modeling and
rendering of a bronze bust of Max Planck, depicted in Fig. 1. First,
the geometry of the bust has been acquired using a 3D scanner. This
initially yields a dense, unstructured set of points in space. This
point cloud has then be triangulated, and the resulting mesh has
subsequently been reduced and compressed. Finally, a novel image-based
method has been used to acquire the texture and reflectance properties
of the bust. Using an optimization process, this data has subsequently
been converted to a sparse representation that is suitable for
hardware rendering. The bronze bust can now be displayed interactively
in real-time from an arbitrary point of view and under arbitrary
lighting conditions.

In this talk I will elaborate on the general framework of 3D Image
Analysis and Synthesis, and will try illustrate the general concept by
means of several examples from current research.


--email hidden
passcode not visible
logged in users only

Bahareh Kadkhodazadeh, 04/19/2005 11:48
Bahareh Kadkhodazadeh, 04/12/2005 12:25
Bahareh Kadkhodazadeh, 04/07/2005 15:59
Bahareh Kadkhodazadeh, 04/07/2005 15:38 -- Created document.