PhD Thesis Topic

We explore the 3D reconstruction of large-scale indoor and outdoor scenes, from raw measurement data. Our focus is on 3D vector maps: semantic-aware representations that exhibit effective complexity-distortion trade offs. Our motivation stems from domain-specific applications e.g. urban planning and safer transportation. Departing from current approaches that determine a single prior for regularizing the inherent ill-posed nature of reconstruction, we plan to find by supervised machine learning a series of priors that locally adapt to the semantic class of objects. Resilience to missing data will be tackled via data-driven completion, and data consolidation will be achieved via joint learning and regularization based on geometric primitives.

The PhD project takes place both at GeometryFactory and at Inria Sophia-Antipolis, who are both partners of the GRAPES Innovative Training Networks. Secondments, that is three month working visits, are planned at RWTH (Aachen, Germany) and at USI (Lugano, Switzerland).

The Candidate

Besides a Master in Computer Science and a flair for geometric algorithms, you must fulfill eligibility requirements which are explained on the GRAPES Network website. This page also gives more information about the salary.

Contact

andreas.fabri@geometryfactory.com

pierre.alliez AT inria.fr