IST Lunch Bunch

In this talk I will discuss a novel paradigm for jointly addressing two fundamental problems in computer vision: scene understanding and scene 3D reconstruction. Most of the state-of-the-art methods deal with these two tasks separately. Methods for object recognition typically describe the scene as a list of class labels, but are unable to account for the 3D spatial structure. Most of the approaches for scene 3D modeling produce accurate metric reconstructions but are unable to infer the semantic content of its components. A major line of work from my lab in recent years is to explore methodologies that seek to fill this gap and to coherently describe objects and object components while simultaneously integrating their 3D spatial arrangement in the scene's physical space. This research is relevant to many application areas including autonomous navigation, robotics and automatic 3D modeling of urban environments.