Logo SceneNet

Audio-Visual Gestalt Workshop

How can multiple audio-visual sources be used to create enhanced user experience?

Bremen (Germany), September 29th - 30th 2014


The Audio-Visual Gestalt Workshop was a great success. We thank all participants for coming to Bremen and the fruitful discussions. We are looking forward to upcoming interesting meetings and collaborations. New infos will follow soon.


This workshop dealt with the concept of combining multiple sources of audio-visual information and user generated contents, in the form of images and videos, to create an enhanced description of a scene that can be shared among users. In this workshop we aim at discussing several aspects of this topic: data acquisition, data synchronization, 3D/4D visual data reconstruction, compute related issues, visualization aspects and last but not least ethical, legal and social questions that arise from this concept.


Representatives from the following projects have participated:

  1. C-Space
  2. HandiCams
  3. Harvest4D
  4. Phenicx
  5. vConect
  6. FOKUS-K3D
  7. ICoSOLE
  8. ROMEO

Please have a look at some presentations from the workshop participants:


Welcome presentation (Chen Sagiv, SagivTech)

c-Space (Bruno Simoes, Fondazione Graphitech)

FOKUS-K3D (Remco Veltkamp, Universiteit Utrecht)

ICoSOLE (Marcus Thaler, Joanneum Research)

ROMEO (Safak Dogan, University of Surrey)

Acquisition and Data Flow (Jürgen Schmidt, Technicolor R&I)

Legal Aspects of Crowd Sourcing of Audio-Visual Information (Franziska Boehm, University of Munster)


For more information please contact

Dr. Chen Sagiv
Phone: +972-9-7411 561


This project is funded by the European Union under the 7th Research Framework, programme FET-Open SME,
Grant agreement no. 309169.
7th Research Framework programme FET-Open SME, Grant agreement no. 309169