Yann Labbé

Core Researcher

H Company

Bio

I am a Core Researcher at H, building AI agents and action models. Prior to H, I was an AI Research Scientist at Meta Reality Labs. I obtained a PhD from Inria Paris and Ecole Normale Supérieure where I was supervised by Josef Sivic. 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. Please reach out for a detailed resume.

Publications

6D Object Pose Tracking in Internet Videos for Robotic Manipulation
Georgy Ponimatkin, Martin Cífka, Tomas Soucek, Médéric Fourmy, Yann Labbé, Vladimir Petrik, Josef Sivic
ICLR 2025

openreview

FoundPose: Unseen Object Pose Estimation with Foundation Features
Evin Pınar Örnek, Yann Labbé, Bugra Tekin, Lingni Ma, Cem Keskin, Christian Forster, Tomas Hodan
ECCV 2024

paper project page

BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects
Tomas Hodan, Martin Sundermeyer, Yann Labbé, Van Nguyen Nguyen, Gu Wang, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Jiri Matas
CVPR Workshops 2024

paper workshop

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare
Martin Cífka, Georgy Ponimatkin, Yann Labbé, Bryan Russell, Mathieu Aubry, Vladimir Petrik, Josef Sivic
TPAMI 2024

paper

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

link

BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objects
Martin Sundermeyer, Tomas Hodan, Yann Labbé, Gu Wang, Eric Brachmann, Bertram Drost, Carsten Rother, Jiri Matas
CVPR Workshops 2023

paper workshop

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

paper project page code openreview

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

paper project page code

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

paper

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).

paper project page code

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

paper

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

paper website workshop

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).

paper project page code video BOP slides

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

paper project page code