# Output-Sensitive Avatar Representations

 

 [ Zum Inhalt springen   ](#stagecontent691805) 

 

 

 



 

  

 

 

 

 

     ![](/fileadmin/_processed_/0/f/csm_2020-output-sensitive_avatar_representations_db4450e3b3.webp)   

Three collocated telepresence participants (including the camera) meet two remote participants in a shared virtual scene. Since the viewing perspectives of the local participants are similar, our output-sensitive avatar reconstruction approach allows for optimized remote avatar reconstruction, network bandwith utilization as well as reduced round trip-times for both parties in group-to-group telepresence scenarios.

 

 

 

 

 

##  Abstract 

 

In this paper, we propose a system design and implementation for output-sensitive reconstruction, transmission and rendering of 3D video avatars in distributed virtual environments. In our immersive telepresence system, users are captured by multiple RGBD sensors connected to a server that performs geometry reconstruction based on viewing feedback from remote telepresence parties. This feedback and reconstruction loop enables visibility-aware level-of-detail reconstruction of video avatars regarding geometry and texture data, and considers individual and groups of collocated users. Our evaluation reveals that our approach leads to a significant reduction of reconstruction times, network bandwidth requirements and round-trip times as well as rendering costs in many situations.

 

 

 

 

 

##  Publication 

 

Adrian Kreskowski, Stephan Beck, and Bernd Froehlich. 2022.
**Output-Sensitive Avatar Representations for Immersive Telepresence
In IEEE Transactions on Visualization and Computer Graphics, vol. 28, no. 7, pp. 2697-2709, 1 July 2022. Presented at IEEE VR 2021, Virtual Event. IEEE Computer Society. DOI: [10.1109/TVCG.2020.3037360](https://doi.org/10.1109/TVCG.2020.3037360 "Öffnet Link")
\[[IEEE](https://ieeexplore.ieee.org/document/9257094 "Öffnet Link")\]\[[preprint](/fileadmin/user/fak/medien/professuren/Virtual_Reality/documents/publications/2020-output-sensitive_avatar_representations_for_immersive_telepresence.pdf "Öffnet Link")\]\[[video](https://www.uni-weimar.de/projekte/vr-scratch/videos/2020-output-sensitive_avatar_representations_for_immersive_telepresence.mp4 "Öffnet Link")\]\[[IEEE VR 2021 Presentation Video](https://www.youtube.com/watch?v=zT1-4IDbFr8&t=21290s "Öffnet Link")\]

 

 

 

 

  <a id="c722197"></a>  

 

 

 

 <a id="c722198"></a>  

 

 

 

 <a id="c722199"></a>  

 

 

 

 <a id="c722200"></a>  

 

 

 

 

 



     Vorheriger Slide       Nächster Slide