Objectives :

 

This course will introduce students to advanced topics in modern geometric 3D data analysis with focus on a) mathematical foundations (discrete differential geometry, mapping, optimization), and b) deep learning for best performing methods. We will give an overview of the foundations in 3D shape analysis and processing before moving to modern techniques based on deep learning for solving problems such as shape classification, correspondence, parametrization, etc.

Content :

 

The course is divided into four lectures and four lab sessions. The topics covered include:

  • Intro to 3D Shape Representaiton and Discrete Differential Geometry,

  • Optimization of geometric energies,

  • Deep learning on curved surfaces,

  • Analysis and machine learning on point clouds

Language :

The course will be taught in English by Maks Ovsjanikov and Etienne Corman.

 

Evaluation :

Oral paper presentation.