PhD positions in Marie Curie ITN-EID project BIGMATH
Two 3-years PhD positions for Early Stage Researchers are offered at Universita' degli Studi di Milano in the framework of the Marie Curie project BIGMATH (For more information on BIGMATH, please visit the web site http://itn-bigmath.unimi.it/).
See also http://www.unimi.it/ricerca/dottorati/96350.htm for the call and specific requirements.
Project A title: Mathematical morphology for the prediction of face expression (ESR2)
The objective of this project is to provide a realistic mathematical description of human face expression transition, for virtual reality applications. Human face expressions can be classified into about 60 different classes, but the transition from one class to another must be sufficiently “smooth” to avoid producing motion and perception artefacts. Actually a linear interpolation between the geometrical descriptions of the different classes in many cases is not sufficiently realistic. Thus the goal of the student enrolled in this project will be to develop and apply new stochastic geometric techniques, nonlinear regressions and non linear optimization techniques to the 4D data scanned from real human face expression, to model correctly the transition of the space-time distributions of the landmarks or surfaces describing the expression. The developed models will take into account both the possible imbalance in the sampling of face expressions and the real-time computability requirements of the company, and will thus be reduced to fasten the computation, and optimized in a distributed manner.
Planned secondments for Project A: The student will spend half of his/her research period at the company 3Lateral, Novi Sad (Serbia)
Project B title: Stochastic Geometric modelling and 3D image analysis for human face prostheses (ESR3)
Extracting usable parametric geometry models from point data is an open challenge. Assuming a set of point clouds obtained from instances of an (unknown) parametric class of 3D objects, the challenge is to recover, by developing suitable statistical methods on manifolds or in non Euclidean spaces, the underlying parametric surface model, knowing that point clouds are corrupted with noise, missing data, outliers and are non-uniformly sampled with different densities. Prior work, describing human lower legs, was capable of achieving the required objectives with a dataset consisting of a hundred human scans. In this project, surface models with high intrinsic curvature will be considered, requiring both different modelling techniques and the creation of much larger real-world datasets. Registration of these datasets in a common reference frame, prior to model extraction, is a common pre-processing operation, consisting of identifying shared features, which can be pre-aligned. The industrial goal for this student will be to recover models of human face features (e.g. ears, noses) for the prosthetic industry, which require high quality colour models. In this setting, model instantiation is constrained by the border conditions of the existing face shape and texture to which the generated model will need to fit.
Planned secondments for Project B: The student will spend half of his/her research period at the company uRoboptics, Lisbon (Portugal)