Professor Daniel Cremers Talk

Next wednesday April 11 at 10:30 in Room 3.2 of "Edificio de Informática y Matemáticas", Professor Daniel Cremers, from Technische Universität München, will present the conference: 

Title: Convex Optimization for Computer Vision

Abstract: Numerous computer vision problems can be solved by variational methods and partial differential equations.  Yet, many traditional approaches correspond to non-convex energies giving rise to suboptimal solutions and often strong dependency on appropriate initialization.  In my presentation, I will show how problems like image segmentation, multiple view reconstruction and optic flow estimation can be formulated as variational problems.  Subsequently, I will introduce methods of convexification which allow to compute globally optimal or near-optimal solutions. The resulting algorithms provide robust solutions, independent of initialization and compare favorable to spatially discrete graph theoretic approaches in terms of computation time, memory requirements and accuracy.