PhD student in Geovic team,

Ecole Polytechnique

I am a Computer Science PhD student advised by Maks Ovsjanikov. My research focuses on 3D shape analysis and processing. I am particularly interested in geometric deep learning approaches.

Email: marie-julie.rakotosaona at polytechnique.edu
Github: https://github.com/mrakotosaon


Learning Delaunay Surface Elements for Mesh Reconstruction

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy J. Mitra, Maks Ovsjanikov

CVPR 2021 (oral)

[Project][Paper][Code][CVPR Daily article]

Correspondence learning via linearly-invariant embedding

Riccardo Marin*, Marie-Julie Rakotosaona*, Simone Metzi, Maks Ovsjanikov
(* joint first authors)

NeurIPS 2020


Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation

Marie-Julie Rakotosaona, Maks Ovsjanikov

ECCV 2020 (oral)


Effective Rotation-invariant Point CNN with Spherical Harmonics kernels

Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty, Maks Ovsjanikov

3DV 2019


OperatorNet: Recovering 3D Shapes From Difference Operators

Ruqi Huang*, Marie-Julie Rakotosaona*, Panos Achlioptas, Leonidas Guibas, Maks Ovsjanikov
(* joint first authors)

ICCV 2019


PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Clouds

Marie-Julie Rakotosaona, Vittorio La Barbera, Paul Guerrero, Niloy J. Mitra, Maks Ovsjanikov

Computer Graphics Forum 2019