DR DOMINIK KULON Curriculum Vitae London, UK
[email on request] P. 01 / 02

Dominik Kulon

CV / ML / Gen AI   / PhD, Computer Vision
[email on request] linkedin.com/in/dkulon dkulon.com

I build machine learning systems that facilitate billions of user interactions at global scale.
My work spans computer vision, generative modelling, and 3D understanding, with products deployed to hundreds of millions of users.

01
Currently
Snap Inc.
ML Engineer
02
Impact
2B+ monthly views
across my AR products
03
Expertise
CV · Gen AI · 3D ML
on-device, real-time
04
Education
Imperial College London
PhD, Computer Vision
§ 01

Career

2019 →
2020+

Machine Learning Engineer

Snap Inc. · London

Built a widely used hand-tracking system for mobile devices; later focused on human video generation and model distillation. Responsible for end-to-end product development, from model training to production deployment.

  • Distilled video diffusion models to transform users into digital characters in real-time on mobile devices.
  • Trained diffusion models for pose-controlled human video generation.
  • Developed a hand tracking system that powers a wide range of AR experiences, reaching over 2B monthly views.
2019–20

Computer Vision Scientist

Ariel AI · London

Early employee; joined during my PhD to bring research into production.

  • Developed a real-time, on-device system for 3D hand mesh reconstruction from 2D images.
  • Built a 3D statistical model of human hands trained on 500k hand scans from 1,300+ individuals.
  • Responsible for large-scale data collection and processing using a 3D motion capture setup.
ACQUIRED BY SNAP
§ 02

Selected projects

Snap · 2020 →
001
2025-26
Snap Inc.

Body Avatars

Examples ↗ Lens Studio Guide ↗ EasyLens Web ↗

Developed a new category of augmented reality products that transform users into digital characters with pixel-level accuracy. The effects operate in real-time on mobile devices. Anyone can create their own character by uploading a single reference image.

Dr Dominik Kulon  ·  Curriculum Vitae  ·  MMXXVI Page 01 / 02 →
DR DOMINIK KULON Curriculum Vitae London, UK
[email on request] P. 02 / 02
§ 02 →

Selected projects (cont'd)

Snap · 2020 →
  • Built data generation pipelines and trained proprietary models for on-device inference.
  • Productionized the system and empowered users with the ability to create their own effects via Lens Studio and EasyLens.
  • Individual effects reached 300M+ views, contributing to several billion views in total.
002
2020-25
Snap Inc

3D Hand Tracking

3D Hand Tracking ↗

Developed a hand tracking system used by hundreds of millions of Snapchatters.

  • Owned end-to-end product development, including model design and training, on-device optimization, data collection, and production deployment.
  • The system became a core component for augmented reality effects, generating over 2B monthly views.
  • Enabled novel brand experiences for major companies such as Disney, Cartier, Dior, Lego, Netflix, Samsung, Coca-Cola, McDonald's, KFC, and many others.
003
2019-20
Imperial College

Hand Shape Modelling

Built a 3D statistical model of human hands trained on 500k hand scans from 1,300+ individuals (ages 3–81).

  • Trained a deformable model of human hands that enables control of bone-length and hand shape variations.
  • Collected and processed a multiview hand scans dataset.
§ 03

Selected publications & patents

2021
Imperial College London
Advancing 3D Hand Reconstruction and Modelling with Geometric Deep Learning
D. Kulon
PHD THESIS
2020
CVPR
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
D. Kulon, R. A. Güler, I. Kokkinos, M. Bronstein, S. Zafeiriou
CVPR BEST PAPER NOMINEE
2019
BMVC
Single Image 3D Hand Reconstruction with Mesh Convolutions
D. Kulon, H. Wang, R. A. Güler, M. Bronstein, S. Zafeiriou
2023
USPTO
Hand Surface Normal Estimation
R. A. Güler, D. Kulon, H. Tam, H. Wang
PATENT
2023
USPTO
Depth Estimation from RGB Images
R. A. Güler, D. Kulon, H. Tam, H. Wang
PATENT
2020
USPTO
Generating Three-Dimensional Object Models from Two-Dimensional Images
D. Kulon, R. A. Güler, I. Kokkinos, S. Zafeiriou
PATENT
§ 04

Education

2014 → 2021
2018–21

PhD, Computer Vision

Imperial College London

Advised by Prof. Stefanos Zafeiriou & Prof. Michael Bronstein.
Thesis: Advancing 3D Hand Reconstruction and Modelling with Geometric Deep Learning.

EPSRC scholarship
2017 – 18

MRes, Advanced Computing

Imperial College London
DISTINCTION
2014 – 17

BSc, Computer Science

King's College London
FIRST-CLASS HONOURS
Dr Dominik Kulon  ·  References available on request  ·  MMXXVI ← Page 02 / 02