Dr. Denis Tomé

Research Scientist

I research at the intersection between computer vision and graphics, to help facilitate the creation of digital humans. From markerless mocap solutions, data driven animation, to tools to easily and quickly help artists in character creation. Examples of work which I contributed to is: products within the Apple Vision Pro lineup, the metahuman creator tool and The Matrix Awakens.
Before that, I worked on solutions for 3D human pose estimation both from external views as well as for VR/AR applications from wearable devices. Such models were designed with limited data availability constraints and with the flexibility to rely on different heterogeneous data sources.
I received my Ph.D. from University College London (UCL) under the supervision of Prof. Lourdes Agapito and Prof. Gabriel Brostow as a member of the Vision and Imaging Science Group. My research was funded by the SecondHands European project.

Experience

Sept. 2022 - Present
Apple, Sunnyvale, CA
Senior Research Engineer, Body
Contributed to the development of products within the Apple Vision Pro lineup
Dec. 2019 - Sept. 2022
EpicGames, Pittsburgh, PA
Research Scientist, Digital Humans
Lead: Iain Matthews
Research and design solutions, both as stand-alone tools or as support in the creation of digital humans. Original contributor of the UE5 metahuman-hair-card-generator
Oct 2019 - Dec 2019
Facebook, London, UK
Research Scientist as contractor, Facebook Reality Lab (FRL)
Designed and developed solutions for the problem of 3D Human Pose Estimation from engocentric perspective, published at PAMI.
Summer 2019
Facebook, Pittsburgh, PA
Research Intern, Facebook Reality Lab (FRL)
Mentor: Hernan Badino, Chenglei Wu
Designed and developed solutions for the problem of 3D Human Pose Estimation from engocentric perspective, published at PAMI.
May 2018 - Nov 2018
Facebook, London, UK
Research Scientist as contractor, Facebook Reality Lab (FRL)
Designed and developed solutions for the problem of 3D Human Pose Estimation from engocentric perspective, published at ICCV'19.
Summer 2018
Facebook, Pittsburgh, PA
Research Intern, Oculus Research
Mentor: Hernan Badino
Designed and developed solutions for the problem of 3D Human Pose Estimation from engocentric perspective, published at ICCV'19.
Aug. 2017 - Nov. 2017
SuperMediaFuture, London, UK
Computer Vision Consultant,
Working on early prototypes of 3D human pose estimation tools for real time applications. This work helped secure $7.5 million in venture capital funding.
Feb. 2016 - Dec. 2019
University College London (UCL), London, UK
Graduate Research Assistant, Vision and Imaging Science Group
Mentor: Lourdes Agapito
Conducted research in semi/self-supervised deep models for 3D pose estimation
Jun. 2015 - Jan. 2016
STMicroelectronics, Milan, IT
Research Intern,
Mentor: Danilo Pau – Senior Principal Engineer - Senior Member of Technical Staff
Researching on problem of pedestrian detection and CNN compression for low power devices. Out of this work I got a fully functional prototype running at 25Hz on a custom low-power device.

Education

Feb. 2016 — Feb. 2020
Ph.D. in Computer Vision
University College London, London, UK
Advisor: Prof. Lourdes Agapito, Co-advisor: Prof. Gabriel Brostow
Thesis: More is Better: 3D Human Pose Estimation from Complementary Data Sources
Sept. 2013 - Oct. 2015
M.S. in Computer Engineering
Polytechnic University of Milan, Milan, Italy
Final mark: 110cum Laude/110 (Graduation with Honor)
Exam average score: 29.45/30 (4.0 GPA Equivalent)
Sept. 2010 - Sept. 2013
B.S. in Computer Engineering
Polytechnic University of Milan, Milan, Italy
Final mark: 103/110

Honors and Awards

2022
CVPR'22 Best Demo Award
For Speech Driven Tongue Animation.
Improve realistic animations & surpass the uncanny valley by enabling data-driven tongue animation
2021
EURASIP Best Paper Award for IMAGE COMMUNICATION Journal
For the work Deep Convolutional Neural Networks for pedestrian detection, D.Tomè, F.Monti, L.Baroffio, L.Bondi, M.Tagliasacchi, S.Tubaro, Image Communication, Volume 47, September 2016, Pages 482-489
2017
Nominated for "Outstanding Support for Teaching"
To be nominated candidates must have made a huge impact on the students they teach and/or support; Among 86 nominees from approx. 7100 academic staff members (less than 1.3%)
http://studentsunionucl.org/student-choice-teaching-awards-roll-of-honour-2017

Publications

EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans
Nicola Garau, Giulia Martinelli, Niccolo Bisagno, Denis Tome, Carsten Stoll
T-CAP Workshop at ECCV. 2024.
Project PDF BibTeX
HumMUSS: Human Motion Understanding using State Space Models
Arnab Mondal, Stefano Alletto, Denis Tome
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2024.
Project PDF Poster BibTeX
Speech Driven Tongue Animation
Salvador Medina, Denis Tome, Carsten Stoll, Mark Tiede, Kevin Munhall, Alex Hauptmann, Iain Matthews
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.
Project PDF Poster Code Data BibTeX Best Demo Award
SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera
Denis Tome, Thiemo Alldieck, Patrick Peluse, Gerard Pons-Moll, Lourdes Agapito, Hernan Badino, Fernando De la Torre
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI). 2020.
Project PDF Data BibTeX DOI
XR-Egopose: Egocentric 3d human pose from an hmd camera
Denis Tome, Patrick Peluse, Lourdes Agapito, Hernan Badino
IEEE/CVF International Conference on Computer Vision (ICCV). 2019.
Project PDF Slides Poster Code Data BibTeX DOI
Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture
Denis Tome, Matteo Toso, Chris Russell, Lourdes Agapito
International conference on 3D vision (3DV). 2018.
Project PDF BibTeX DOI
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image
Denis Tome, Chris Russell, Lourdes Agapito
IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017.
Project PDF Slides Poster Code BibTeX DOI
Reduced memory region based deep Convolutional Neural Network detection
Denis Tome, Luca Bondi, Luca Baroffio, Stefano Tubaro, Emanuele Plebani, Danilo Pau
IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin). 2016.
Project PDF BibTeX DOI
Deep convolutional neural networks for pedestrian detection
Denis Tome, Federico Monti, Luca Baroffio, Luca Bondi, Marco Tagliasacchi, Stefano Tubaro
Signal processing: image communication. 2016.
Project PDF Code BibTeX DOI

Teaching

Feb. 2016 - Dec. 2019
Teaching assistant
University College London (UCL), London, UK
COMP0026-A7P-T1, COMP0026-A6U-T1 Image Processing, Instructor: Prof. Lourdes Agapito
Overviewing labs, mentor students in their group projects. Correct assignments and examine students in the final test.
Feb. 2016 - Dec. 2019
Teaching assistant
University College London (UCL), London, UK
COMP211P Introduction to Programming, Instructor: Prof. Rae Harbird
Overviewing labs, mentor students in their group projects. Correct assignments.

References

Dr. Lourdes Agapito, Professor of 3D Vision, Programme Director, MSc Computer Graphics Vision and Imaging
Vision and Imaging Science Group
University College London (UCL)
Email: l.agapito@cs.ucl.ac.uk
Dr. Hernan Badino, Research Scientist
Facebook Reality Lab
Facebook (META)
Email: hernan.badino@fb.com
Dr. Fernando De la Torre, Research Associate Professor
Robotics Institute
Carnegie Mellon University (CMU)
Email: ftorre@cs.cmu.edu
Francisco Vincente, Lead Research Engineer
Studio Research
Epic Games
Email: franciscovicencar@gmail.com