Abstract: Reconstructing and synthesizing 3D humans in 3D scenes is an important topic in computer vision and graphics. In this talk, I will present three lines of work. First, I will discuss the challenges and methods of reconstructing 3D humans from monocular videos, with a particular focus on ego-centric perspectives. Second, I will discuss our recent work on synthesizing natural and spontaneous human behaviors within 3D scenes. Last, I will present the application of our human motion synthesis models for the generation of synthetic datasets, thereby facilitating the training of more robust human segmentation models.
Bio: Siyu Tang has been an Assistant Professor at ETH Zürich since January 2020, leading the Computer Vision and Learning Group (https://vlg.inf.ethz.ch). She was a postdoctoral researcher at the Max Planck Institute for Intelligent Systems, supervised by Dr. Michael Black. In 2017, Siyu obtained her Ph.D. from the Max Planck Institute for Informatics, supervised by Prof. Bernt Schiele. Before moving to Europe, she studied computer science at Zhejiang University in China. She has received several awards for her research, including the Best Paper Awards at BMVC 2012 and 3DV 2020, Best Paper Award Candidates at CVPR 2021 and CVPR 2022, Outstanding Paper Finalist for Physical Human-Robot Interaction at ICRA 2023, an ELLIS Ph.D. Award and a DAGM-MVTec Dissertation Award.
