Event Location: NSH 1507
Bio: Sofien Bouaziz is a PhD student in the Computer Graphics and Geometry Laboratory at École Polytechnique Fédérale de Lausanne (EPFL). He received an MSc degree in Computer Science from EPFL in 2009 and completed his master thesis at the Imaging Group of Mitsubishi Electric Research Laboratories, where he developed computer vision algorithms for car geolocalization in urban areas. After his graduation and before starting a PhD in 2010, he joined E-ON Software as an R&D software engineer where he developed robust geometry processing algorithms and worked on physical simulations of natural phenomena. His research interests include computer graphics, computer vision and machine learning. In 2012, Sofien co-founded Faceshift AG, a startup company which brings high-quality markerless facial motion capture to the consumer market. Besides his passion for science and research, Sofien likes to play piano and enjoys composing music.

Abstract: Recent advances in realtime performance capture and virtual reality have brought within reach a new form of human communication. Capturing dynamic facial expressions of a user and retargeting these expressions to a digital character in realtime allows enacting arbitrary virtual avatars with live feedback. Compared to communication via recorded video streams that only offer limited ability to alter one’s appearance, such technology opens the door to fascinating new applications in computer gaming, social networks, television, training, customer support, or other forms of online interactions. In this talk, I will present a new pipeline for realtime face tracking and modeling on commodity RGB-D sensing devices, e.g. Kinect. Our method requires no user-specific training or calibration, or any other form of manual assistance, thus enabling a range of new applications in performance-based animation and virtual interaction at the consumer level. In a live demo, I will demonstrate that compelling 3D facial dynamics can be reconstructed in realtime without the use of face markers, intrusive lighting, or complex scanning hardware.