Within the InterDigital Immersive lab. in Rennes, France (https://www.interdigital.com/video-resources/), the postdoc researchers will be part of a team developing techniques and solutions addressing the large domain of Digital Humans. It includes modeling, animation, personalization, interactions and several other aspects of the virtual representation of the human society.
InterDigital already developed and demonstrated solutions for capturing and modeling faces (FMX’19, SIGGRAPH’19, IEEE VR’19), and the objective of these post-docs is to extend this work.
The research directions will focus on the capture and modeling of faces and bodies. You will work within an international research organization at the boundary between computer vision, computer graphics, artificial and human intelligence.
What you will be doing:
- Invent, implement and validate new technical concepts according to the team strategy,
- Participate to the research valorization effort through invention disclosures, technology transfers, demonstrations and publications in peered-review journals and prestigious conferences,
- Propose new research directions to feed InterDigital innovation.
 F. Danieau, I. Gubins, N. Olivier, O. Dumas, B. Denis, T. Lopez, N. Mollet, B. Frager and Q. Avril. "Automatic Generation and Stylization of 3D Facial Rigs.", IEEE VR 2019.
 Achenbach, Jascha, Thomas Waltemate, Marc Erich Latoschik, and Mario Botsch. “Fast Generation of Realistic Virtual Humans,” 2017.
 Bönsch, Andrea, Andrew Feng, Parth Patel, and Ari Shapiro. “Volumetric Video Capture Using Unsynchronized, Low-Cost Cameras:” In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 255–61. Prague, Czech Republic, 2019.
 Ma, Qianli, Siyu Tang, Sergi Pujades, Gerard Pons-Moll, Anurag Ranjan, and Michael J. Black. “Dressing 3D Humans Using a Conditional Mesh-VAE-GAN.” ArXiv:1907.13615 [Cs], July 31, 2019.
 Marc Habermann1 Weipeng Xu1 Michael Zollhoefer2 Gerard Pons-Moll1 Christian Theobalt. “Real-time Human Performance Capture from Monocular Video” ACM Trans. Graph. 2019
Skills and Qualifications:
PhD in computer graphics, computer vision or related field.
Expertise in the topic of simulation, 3D modeling, animation
Strong experience in SW development (python/c++)
Some experience in Machine Learning / Deep Learning
Experience with photogrammetry would be a plus
Proven track record in publications, technical innovation and problem solving
Team spirit, enthusiastic, motivated, and creative attitude
Good communication skills to promote activities internally and externally. Fluent English mandatory