The next IC Colloquium will welcome Siyu Tang, assistant professor at ETH Zürich. Siyu Tang’s research focuses on computer vision and machine learning, with a specialization in human perception and modeling. For this event, free and open to all, she will present her work on the development of realistic human avatars.
Photorealistic reconstruction and animation of clothed human avatars is a long-standing problem in computer vision and graphics. While existing solutions can achieve photorealistic reconstruction for head and body avatars given dense camera views, challenges remain under sparse multi-view/monocular setups. Meanwhile, there is no existing solution to automatically populate a digital world with realistic digital humans who move and act like real ones. In this talk, I will present our previous and ongoing research on creating and animating human avatars that look, move, and behave realistically in digital environments.
Siyu Tang has been an assistant professor at ETH Zürich since January 2020. She leads the Computer Vision and Learning group (https://vlg.inf.ethz.ch). She was a postdoctoral researcher at the Max Planck Institute for Intelligent Systems, advised by Dr. Michael Black. She obtained her Ph.D. at the Max Planck Institute for Informatics in 2017 under the supervision of Prof. Bernt Schiele. Before that, she received her Master’s degree in Media Informatics at RWTH Aachen University and her Bachelor’s degree in Computer Science at Zhejiang University. She has received several awards for her research, including the Best Paper Award at BMVC 2012 and 3DV 2020, Best Paper Award Candidates at CVPR 2021, CVPR 2022, and an ELLIS Ph.D. Award and a DAGM-MVTec Dissertation Award.