Yann Labbé

Yann Labbé

Research Scientist

Meta Reality Labs

Bio

I am a Research Scientist at Meta Reality Labs in Zurich. I obtained a PhD from Inria Paris and Ecole Normale Supérieure where I was supervised by Josef Sivic. Before the PhD, I graduated from Ecole Normale Supérieure de Cachan where I received a dual Masters degree in Mathematics, Machine Learning, Computer Vision (MVA) and in Electrical Engineering (E3A) with highest honors. In 2017, I was among the top candidates at the nationwide competition Agrégation in Electrical Engineering. I was an intern at Nvidia in 2022 and Chronocam (now Prophesee) in 2016.

Publications


PhD thesis
Pose estimation of rigid objects and robots
Yann Labbé
PhD Thesis, 2023.

MegaPose
MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare
Yann Labbé, Lucas Manuelli, Arsalan Mousavian, Stephen Tyree, Stan Birchfield, Jonathan Tremblay, Justin Carpentier, Mathieu Aubry, Dieter Fox, Josef Sivic
CoRL 2022.

FocalPose
Focal Length and Object Pose Estimation via Render and Compare
Georgy Ponimatkin, Yann Labbé, Bryan Russel, Mathieu Aubry, Josef Sivic
CVPR 2022.

CosySLAM
CosySlam: investigating object-level SLAM for detecting locomotion surfaces
César Debeunne, Médéric Fourmy, Yann Labbé, Pierre-Alexandre Léziart, Guilhem Saurel, Joan Solà, Nicolas Mansard
Preprint, 2022.

RoboPose
Single-view robot pose and joint angle estimation via render & compare
Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic
CVPR 2021.
Accepted as oral (top 4% submissions).

CosyPose
CosyPose: Consistent multi-view multi-object 6D pose estimation
Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic
Preprint, 2021.
Journal version of the ECCV paper.

BOP
BOP Challenge 2020 on 6D Object Localization
Tomas Hodaň, Martin Sundermeyer, Bertram Drost, Yann Labbé, Eric Brachmann, Frank Michel, Carsten Rother, Jiri Matas
ECCVW 2020.

CosyPose
CosyPose: Consistent multi-view multi-object 6D pose estimation
Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic
ECCV 2020.
Winner of the BOP Challenge at ECCV 2020 (5/6 awards).

MCTS
Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning
Yann Labbé, Sergey Zagoruyko, Igor Kalevatykh, Ivan Laptev, Justin Carpentier, Mathieu Aubry, Josef Sivic
RAL 2020.