Virtual VASC Seminar:  https://cmu.zoom.us/j/249106600

Title:  End-to-end Generative 3D Human Shape and Pose Models and Active Human Sensing

Abstract:  I will review some of our recent work in 3d human modeling, synthesis, and active vision. I will present our new, end-to-end trainable nonlinear statistical 3d human shape and pose models of different resolutions (GHUM and GHUMLite) as well as on methods to reconstruct complex scenes where people are in contact and involved in interactions. I will also cover self-supervised active triangulation for 3d human sensing where an intelligent agent relies on deep reinforcement learning to identify policies that lead to optimal camera placement for informative scene observation, improved accuracy and speed. Time permitting, I will also illustrate 3d appearance modeling and geometrically consistent scene-insertion methods that support realistic human synthesis and scene composition for e.g. special effects or large scale model training.

This is joint work with H. Xu, E. Bazavan, A. Zanfir, M. Fieraru, E. Oneata, A. Popa, M. Zanfir, E. Gartner A. Pirinen, R. Sukthankar and B. Freeman.

Bio:  Cristian Sminchisescu is a Research Scientist leading a team at Google, and a Professor at Lund University. He has obtained a doctorate in computer science and applied mathematics with focus on imaging, vision and robotics at INRIA, under an Eiffel excellence fellowship of the French Ministry of Foreign Affairs, and has done postdoctoral research in the Artificial Intelligence Laboratory at the University of Toronto. He has held a Professor equivalent title at the Romanian Academy and a Professor rank, status appointment at Toronto, and has advised research at both institutions. During 2004-07, he was a faculty member at the Toyota Technological Institute at the University of Chicago, and later on the Faculty of the Institute for Numerical Simulation in the Mathematics Department at Bonn University. Cristian Sminchisescu regularly serves as an Area Chair for computer vision and machine learning conferences (CVPR, ECCV, ICCV, AAAI, NeurIPS), has been a Program Chair for ECCV 2018, and an Associate Editor of IEEE Transactions for Pattern Analysis and Machine Intelligence (PAMI) and the International Journal of Computer Vision (IJCV). Over time, his work has been funded by the US National Science Foundation, the Romanian Science Foundation, the German Science Foundation, the Swedish Science Foundation, the European Commission under a Marie Curie Excellence Grant, and the European Research Council under a Consolidator Grant. Cristian’s research interests are in the area of computer vision (3d human sensing, reconstruction and recognition) and machine learning (optimization and sampling algorithms, kernel methods and deep learning). His work on deep learning of graph matching has received the best paper award honorable mention at CVPR 2018.

Homepage:

http://www.maths.lth.se/sminchisescu/
https://research.google/people/CristianSminchisescu/

Sponsored in part by:   Facebook Reality Labs Pittsburgh