A Superresolution Framework for High-Accuracy Multiview Reconstruction

Focus of this talk are the current state-of-the-art methods for 3D reconstruction from multiple calibrated views which were developed in our group.

Based on a convex formulation for the 3D reconstruction problem, an initial 3D model is obtained. The geometry is further refined in a combined variational approach to jointly estimate a displacement map and a super-resolved texture for the model. The super-resolution approach to texture reconstruction allows to obtain fine details in the texture map which surpass individual input image resolution Some of the interesting mathematical background can be applied quite generally and is briefly discussed. This includes convex relaxation techniques for global optimization of certain total variation based energy functionals, as well as an algorithm for solving partial differential equations on surfaces.