Robust learning-based methods for shape correspondence

I am a professor of computer science at Ecole Polytechnique. Prior to this, I worked for Google in their Image Search team in sunny Mountain View. In 2011 I graduated from Stanford University with a Ph.D. in Computational Mathematics (from the ICME department), having done work on shape analysis in the geometric computing lab headed by prof. Leonidas Guibas. In 2014, I received the Eurographics Young Researcher Award. In 2018, I received a Bronze medal from the CNRS. My CV from October 2018 can be found here.

Abstract

In this talk I will describe several recent works aimed at developing accurate and robust methods for non-rigid 3D shape matching and comparison. I will first describe several ways to model this problem, including supervised, unsupervised and weakly supervised training losses. In addition, I will highlight several recent architectures, focusing especially on spectral methods, that are well adapted to computing dense correspondences across a variety of settings. My ultimate goal will be to show that these techniques are becoming remarkably robust and universally applicable and useful.