Tomas Hodan

Tomas Hodan

AI Scientist at Mistral

About me Updates Publications PhD thesis Activities Awards

About me

I am an AI Scientist at Mistral in Paris, working on multimodal large language models and robotics. Previously I was a Staff Research Scientist at Meta in Seattle and Zurich, where I worked on spatial AI for AR/VR and robotics. I created and lead the BOP benchmark, which became the standard for evaluating 6DoF object pose estimation. My work also includes methods (e.g., FoundPose, EPOS, LISA, NCF, CNOS) and datasets (e.g., HOT3D, T-LESS, BlenderProc) for pose estimation and detection of objects and hands. Beyond research, I organize the R6D workshops and serve as an Area Chair at major vision conferences. I received my PhD in computer vision advised by Prof. Jiri Matas at the Czech Technical University in Prague, during which I interned at Microsoft Research and Google.

Updates

2026/09/08 – 
Organizing the 11th R6D Workshop at ECCV 2026 in Malmö.
2026/06/03 – 
HOT3D received the EgoVis 2024/2025 Distinguished Paper Award.
2026/06/03 – 
Co-organized the 1st Sense of Space Workshop at CVPR 2026 in Denver.
2026/05/11 – 
Joining Mistral in Paris as an AI Scientist, working on multimodal LLMs and robotics.
2026/02/21 – 
2 papers accepted at CVPR 2026 (SHOW3D and EgoPoseFormer v2).
2026/01/01 – 
Serving as an Area Chair for CVPR 2026 and ECCV 2026.
2025/10/19 – 
Organized the 10th R6D Workshop at ICCV 2025 in Honolulu.
2025/06/12 – 
AssemblyHands received the EgoVis 2023/2024 Distinguished Paper Award.
2025/06/11 – 
BOP 2024 report received Best Paper Award at CV4MR Workshop at CVPR 2025.
2025/03/07 – 
BOP Challenge 2025 opened and awaits your submissions!
2025/03/07 – 
Co-organizing Perception Challenge for Bin-Picking and PIRA Workshop at CVPR 2025.
2025/02/26 – 
HOT3D accepted (as highlight) to CVPR 2025 in Nashville.
2025/01/01 – 
Serving as an Area Chair for CVPR 2025.
2024/10/03 – 
FoundPose presented at ECCV 2024 in Milan.
2024/09/29 – 
Organized the 9th R6D Workshop at ECCV 2024 in Milan (recording).
2024/06/13 – 
HOT3D dataset released!
2024/05/29 – 
BOP Challenge 2024 opened.
2024/04/04 – 
Invited talk at 47th PR&CV Colloquium in Prague (slides).
2023/10/03 – 
Organized the 8th R6D Workshop at ICCV 2023 in Paris.
2023/07/06 – 
BOP Challenge 2023 opened.
2023/02/27 – 
Two papers accepted to CVPR 2023 (In-hand 3D object scanning and AssemblyHands).
2023/02/25 – 
BOP'22 report is on arXiv and will be published at CV4MR workshop at CVPR 2023.
2023/01/16 – 
Received the Rector's Prize for an outstanding PhD thesis.
2022/07/08 – 
Neural Correspondence Field accepted to ECCV 2022 in Tel-Aviv.
2022/05/01 – 
BOP Challenge 2022 opened.
2022/05/01 – 
Organizing the 7th R6D Workshop at ECCV 2022 in Tel-Aviv.
2022/03/01 – 
LISA, our neural hand model, accepted to CVPR 2022 in New Orleans.
2021/07/07 – 
PhD defended! A recording of the defense is available on YouTube.
2020/11/02 – 
Joining Facebook Reality Labs in Redmond as a Research Scientist.
2020/10/02 – 
Code and pre-trained models of EPOS are available on GitHub.
2020/09/15 – 
An analysis of the BOP Challenge 2020 results is now available in an ECCVW 2020 paper.
2020/07/12 – 
A paper about BlenderProc accepted to the Sim2Real Workshop at RSS 2020.
2020/07/03 – 
A paper on learning surrogates accepted to ECCV 2020.
2020/06/05 – 
BOP Challenge 2020 announced, together with BlenderProc4BOP.
2020/04/01 – 
EPOS, our CVPR 2020 paper, is now available on arXiv.org.
2020/02/16 – 
Organizing the 6th R6D Workshop at ECCV 2020 in Glasgow.
2019/11/17 – 
Photorealistic synthetic images from our ICIP'19 paper released.
2019/07/26 – 
BOP Challenge 2019 has been opened.
2019/05/20 – 
Invited talk at Siemens AG Research & Technology Center in Munich.
2019/05/01 – 
Organizing the 5th R6D Workshop at ICCV 2019 in Seoul.
2019/04/30 – 
Our paper with Microsoft Research accepted to ICIP 2019 in Taipei.
2018/11/19 – 
Internship at Google in Munich, working with Stefan Hinterstoisser.
2018/09/09 – 
Organizing the 4th R6D Workshop at ECCV 2018 in Munich.
2018/07/03 – 
Our BOP paper accepted to ECCV 2018 in Munich.
2018/06/04 – 
Internship at MSR in Redmond, with Vibhav Vineet, Sudipta Sinha, Brian Guenter.
2017/08/11 – 
Colloquium talk about 6D object pose estimation at the Tampere University.
2017/05/06 – 
Organizing the 3rd R6D Workshop at ICCV 2017 in Venice.
2017/03/28 – 
T-LESS presented at WACV 2017 in Santa Rosa.
Show more

Publications

See my Google Scholar profile for a full list.

SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild
Patrick Rim, Kevin Harris, Braden Copple, Shangchen Han, Xu Xie, Ivan Shugurov, Sizhe An, He Wen, Alex Wong, Tomas Hodan, Kun He
CVPR 2026, Denver
Paper Web
EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR
Zhenyu Li, Sai Kumar Dwivedi, Filip Maric, Carlos Chacon, Nadine Bertsch, Filippo Arcadu, Tomas Hodan, Michael Ramamonjisoa, Peter Wonka, Amy Zhao, Robin Kips, Cem Keskin, Anastasia Tkach, Chenhongyi Yang
CVPR 2026, Denver – Accepted as highlight
Paper
HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos
Prithviraj Banerjee, Sindi Shkodrani, Pierre Moulon, Shreyas Hampali, Shangchen Han, Fan Zhang, Linguang Zhang, Jade Fountain, Edward Miller, Selen Basol, Richard Newcombe, Robert Wang, Jakob Julian Engel, Tomas Hodan
CVPR 2025, Nashville – Accepted as highlight
Paper Web Poster
GoTrack: Generic 6DoF Object Pose Refinement and Tracking
Van Nguyen Nguyen, Christian Forster, Sindi Shkodrani, Vincent Lepetit, Bugra Tekin, Cem Keskin, Tomas Hodan
CVPR Workshops (CV4MR) 2025, Nashville
Paper Code
BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation
Van Nguyen Nguyen, Stephen Tyree, Andrew Guo, Médéric Fourmy, Anas Gouda, Taeyeop Lee, Sungphill Moon, Hyeontae Son, Lukas Ranftl, Jonathan Tremblay, Eric Brachmann, Bertram Drost, Vincent Lepetit, Carsten Rother, Stan Birchfield, Jiri Matas, Yann Labbé, Martin Sundermeyer, Tomas Hodan
CVPR Workshops (CV4MR) 2025, Nashville – CV4MR Best Paper Award
Paper Web Poster
DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions
Sammy Christen, Shreyas Hampali, Fadime Sener, Edoardo Remelli, Tomas Hodan, Eric Sauser, Shugao Ma, Bugra Tekin
SIGGRAPH Asia 2024, Tokyo
Paper Web
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, Milan
Paper Web Code Poster
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 (CV4MR) 2024, Seattle
Paper Web
CNOS: A Strong Baseline for CAD-based Novel Object Segmentation
Van Nguyen Nguyen, Thibault Groueix, Georgy Ponimatkin, Vincent Lepetit, Tomas Hodan
ICCV Workshops (R6D) 2023, Paris
Paper Code
In-Hand 3D Object Scanning from an RGB Sequence
Shreyas Hampali, Tomas Hodan, Luan Tran, Lingni Ma, Cem Keskin, Vincent Lepetit
CVPR 2023, Vancouver
Paper Web Video BibTeX
AssemblyHands: Towards Egocentric Activity Understanding via 3D Hand Pose Estimation
Takehiko Ohkawa, Kun He, Fadime Sener, Tomas Hodan, Luan Tran, Cem Keskin
CVPR 2023, Vancouver – EgoVis 2023/2024 Distinguished Paper Award
Paper Web
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 (CV4MR) 2023, Vancouver
Paper Web BibTeX
UmeTrack: Unified Multi-View End-to-End Hand Tracking for VR
Shangchen Han, Po-chen Wu, Yubo Zhang, Beibei Liu, Linguang Zhang, Zheng Wang, Weiguang Si, Peizhao Zhang, Yujun Cai, Tomas Hodan, Randi Cabezas, Luan Tran, Muzaffer Akbay, Tsz-Ho Yu, Cem Keskin, Robert Wang
SIGGRAPH Asia 2022, Daegu
Paper Code
Neural Correspondence Field for Object Pose Estimation
Lin Huang, Tomas Hodan, Lingni Ma, Linguang Zhang, Luan Tran, Christopher Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, Robert Wang
ECCV 2022, Tel-Aviv
Paper Code Web
LISA: Learning Implicit Shape and Appearance of Hands
Enric Corona, Tomas Hodan, Minh Vo, Francesc Moreno-Noguer, Chris Sweeney, Richard Newcombe, Lingni Ma
CVPR 2022, New Orleans
Paper Web
BOP Challenge 2020 on 6D Object Localization
Tomas Hodan, Martin Sundermeyer, Bertram Drost, Yann Labbé, Eric Brachmann, Frank Michel, Carsten Rother, Jiri Matas
ECCV Workshops (R6D) 2020, Glasgow
Paper Web Workshop BibTeX
Learning Surrogates via Deep Embedding
Yash Patel, Tomas Hodan, Jiri Matas
ECCV 2020, Glasgow
Paper Video BibTeX
BlenderProc: Reducing the Reality Gap with Photorealistic Rendering
Maximilian Denninger, Martin Sundermeyer, Dominik Winkelbauer, Dmitry Olefir, Tomas Hodan, Youssef Zidan, Mohamad Elbadrawy, Markus Knauer, Harinandan Katam, Ahsan Lodhi
RSS Workshops 2020, Corvallis
Paper Code Video BibTeX
EPOS: Estimating 6D Pose of Objects with Symmetries
Tomas Hodan, Daniel Barath, Jiri Matas
CVPR 2020, Seattle
Paper Code Web Video Demo BibTeX
Photorealistic Image Synthesis for Object Instance Detection
Tomas Hodan, Vibhav Vineet, Ran Gal, Emanuel Shalev, Jon Hanzelka, Treb Connell, Pedro Urbina, Sudipta N. Sinha, Brian Guenter
ICIP 2019, Taipei
Paper Dataset Slides BibTeX
BOP: Benchmark for 6D Object Pose Estimation
Tomas Hodan, Frank Michel, Eric Brachmann, Wadim Kehl, Anders Glent Buch, Dirk Kraft, Bertram Drost, Joel Vidal, Stephan Ihrke, Xenophon Zabulis, Caner Sahin, Fabian Manhardt, Federico Tombari, Tae-Kyun Kim, Jiri Matas, Carsten Rother
ECCV 2018, Munich
Paper Web Slides Poster BibTeX
T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects
Tomas Hodan, Pavel Haluza, Stepan Obdrzalek, Jiri Matas, Manolis Lourakis, Xenophon Zabulis
WACV 2017, Santa Rosa
Paper Web Slides Poster BibTeX
On Evaluation of 6D Object Pose Estimation
Tomas Hodan, Jiri Matas, Stepan Obdrzalek
ECCV Workshops 2016, Amsterdam
Paper Slides Code BibTeX
Detection and Fine 3D Pose Estimation of Texture-less Objects in RGB-D Images
Tomas Hodan, Xenophon Zabulis, Manolis Lourakis, Stepan Obdrzalek, Jiri Matas
IROS 2015, Hamburg
Paper Slides Video BibTeX
Efficient Texture-less Object Detection for Augmented Reality Guidance
Tomas Hodan, Dima Damen, Walterio Mayol-Cuevas, Jiri Matas
ISMAR Workshops 2015, Fukuoka
Paper BibTeX

PhD thesis

Pose Estimation of Specific Rigid Objects
Supervisor: Prof. Jiri Matas
Reviewers: Prof. Vincent Lepetit, Prof. Markus Vincze, Dr. Slobodan Ilic
Czech Technical University in Prague, 2021
Received the Rector's Prize for an outstanding PhD thesis
Thesis Defense Slides BibTeX

Activities

Organized BOP challenges on object pose estimation:

Organized R6D workshops on object pose estimation:

Other co-organized events:

Awards