I am interested in recovering physical properties of general scenes from images. My current research focuses on reconstructing dense 3-d surface geometry, appearance and motion of dynamic scenes from multi-view image sequences. I believe accurate estimation of these properties will help understand the physical world.
I am interested in estimating 3D scene representations from multi-view video sequences. In particular, I focus on combining semantic segmentation, object detection and classification with 3D reconstruction using efficient inference methods.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems