Computer Vision for Graphics and Interaction

Catalog description

Computer vision reconstructs real world information from image and video data; computer graphics synthesizes dynamic virtual worlds; interaction lets us explore these worlds; and machine learning allows us to map between domains across vision, graphics, and interaction. In visual computing, these fields converge to exploit both models of visual appearance and databases of examples to generate and interact with new images. This enables applications from the seemingly simple, like semantic photo editing, to the seemingly science fiction, like mixed reality. In this seminar, we will discover the state-of-the-art algorithmic contributions in computer vision which make this possible. Please join us!