Humans are arguably the most interesting subjects in computer vision. Modeling human 3D geometry from images captured by highly sophisticated production level cameras (10-100 cameras with precise calibration) enable a number of applications, e.g. telepresence, virtual try-on, motion analysis, etc. Despite its production level quality, the…

We propose a robust framework for clustering data. In practice, data obtained from real measurement devices can be incomplete, corrupted by gross errors, or not correspond to any assumed model. We show that, by properly harnessing the intrinsic low-dimensional structure of the data, these kinds of practical problems can be dealt with in a uniform…

Students are asked to analyze a photo of a beer stein, computing volumes and areas based on the photo.