January 11th, 2023 
Daniela Lopez de Luise Date&Time: January 12, 2023 at 12:30 p.m. CET [06:30 a.m. New-York] – [12:30 p.m. Paris/Berlin] – [6:30 p.m. Beijing]
Title: Generative Volumetric Video for Interactive Virtual Humans.
Title: Generative Volumetric Video for Interactive Virtual Humans.
Speaker: Peter EISERT (Humboldt University BerlinFraunhofer HHI)
To join the webinar, please register to receive more details on how to connect.
The registration form can be found at: https://forms.gle/9JCc6NBgM1x2kZK6A
or via the website of the journal at: https://jivp-eurasipjournals.springeropen.com/
Contact: Esinu Abadjivor <esinu.abadjivor@springernature.com>
Abstract: Photo-realistic modelling and rendering of humans is extremely important for virtual reality (VR) environments, as the human body and face are highly complex and exhibit large shape variability but also, especially, as humans are extremely sensitive to looking at humans. Further, in VR environments, interactivity plays an important role. While purely computer graphics modeling can achieve highly realistic human models, achieving real photo-realism with these models is computationally extremely expensive. Hence, more and more hybrid methods have been proposed in recent years. In this talk, the creation of high-quality animatable volumetric video content of human performances is addressed. Recent progress in learning human motion and appearance, neural rendering, and implicit function rendering (e.g. NeRF) enable the creation of realistic representation of virtual humans. We combine these approaches with classical models in order to obtain full control for body and face animation. Different concepts ranging from animatable volumetric video to pure data driven representation will be presented that target the realistic animation of virtual humans for different applications.
Contact: Esinu Abadjivor <esinu.abadjivor@springernature.com>
Abstract: Photo-realistic modelling and rendering of humans is extremely important for virtual reality (VR) environments, as the human body and face are highly complex and exhibit large shape variability but also, especially, as humans are extremely sensitive to looking at humans. Further, in VR environments, interactivity plays an important role. While purely computer graphics modeling can achieve highly realistic human models, achieving real photo-realism with these models is computationally extremely expensive. Hence, more and more hybrid methods have been proposed in recent years. In this talk, the creation of high-quality animatable volumetric video content of human performances is addressed. Recent progress in learning human motion and appearance, neural rendering, and implicit function rendering (e.g. NeRF) enable the creation of realistic representation of virtual humans. We combine these approaches with classical models in order to obtain full control for body and face animation. Different concepts ranging from animatable volumetric video to pure data driven representation will be presented that target the realistic animation of virtual humans for different applications.
Speaker Bio: Peter Eisert is Professor for Visual Computing at Humboldt University Berlin and heading the heading the Vision & Imaging Department at Fraunhofer HHI. In 2000, he got his PhD “with highest honors” from the University of Erlangen. In 2001, he worked as a postdoctoral fellow at the Stanford University. He has coordinated and initiatied numerous national and international 3rd party funded projects with a total budget of more than 25 Mio Euros. He has published more than 250 papers and is Associate Editor of the International Journal of Image and Video Processing as well as the Journal of Visual Communication and Image Representation. His research interests include 3D image analysis and synthesis, face body processing, computer vision, computer graphics, as well as deep learning in application areas like multimedia, production, security and medicine.
Webinar videos are available online at https://vimeo.com/showcase/8005816.
Posted in