Maks Ovsjanikov

I am a professor in the Computer Science department at Ecole Polytechnique in France. I am a member of the GeoViC group at the LIX research laboratory of Ecole Polytechnique and an associate member (external collaborator) of the DataShape team at INRIA. My current research is mainly supported by my ERC Starting Grant: EXPROTEA.

My research is primarily related to geometric (3D) shape analysis with emphasis on Deep Learning for non-rigid shape comparison and processing. In the past, I have worked on topics including shape classification and retrieval, non-rigid shape-matching, comparison, denoising and symmetry detection especially on 3D point cloud and triangle mesh data. I'm also very interested in image processing, Computer Graphics and Computer Vision in general. You can find some of my work on the Publications page.

Recent News

April 2023

Our paper TIDE: Time Derivative Diffusion for Deep Learning on Graphs with Maximilian Krahn and Maysam Behmanesh has been accepted at ICML 2023. This paper presents an efficient method for learning on graphs that allows long-range communication without oversmoothing, and, at the same time, inherits the full expressive power of local message passing approaches.

March 2023

Three of our papers have been accepted at CVPR 2023:

• Affection: Learning Affective Explanations for Real-World Visual Data with Panos Achlioptas, Leonidas Guibas, and Sergey Tulyakov,
• Generalizable Local Feature Pre-training for Deformable Shape Analysis with Souhaib Attaiki and Lei Li, and
• Understanding and Improving Features Learned in Deep Functional Maps with Souhaib Attaiki
The last two papers were both accepted as highlights (10% of accepted papers, 2.5% of submissions).

February 2023

While not research related, perhaps the most important news of all, our baby daughter Ida was born in February 2023! Her mother and her are both doing well (to the extent possible).

January 2023

I'm very happy and honored to have just received an ERC Consolidator Grant for my project VEGA: Universal Geometric Transfer Learning. This project will explore ways in which 3D geometric data can be made more amenable to learning, especially in the presence of limited labeled training data. The official announcement is here. As always, I'm looking for motivated PhD and Postdoc candidates!

Two of my outstanding PhD students have successfully defended their PhDs in January 2023:

• Nicolas Donati with his dissertation on Robust representations for supervised and unsupervised 3D shape matching, and
• Mariem Mezghanni with her dissertation Structural and Functional Learning for Industrial Design Automatization, done in partnership with Dassault Systèmes.
Congratulations to Nicolas and Mariem!