The last decade has seen a revolution in the theory and application of computer vision. I will begin with a brief review of some of the fundamentals with a few examples of the reconstruction, registration and recognition of three-dimensional objects from uncalibrated images and their translation into novel commercial applications.
I will then introduce some recent results from real-time deep learning systems that fully exploit geometry, compute model uncertainty and require very small amounts of labelled data. In particular, we will explore the use of geometry to help design networks that can be trained with unlabelled data for human body pose and robot localisation.
09/03/2022