CV
Basics
| Name | Alexandre Symeonidis-Herzig |
| Label | PhD Researcher in Computer Vision |
| a.symeonidisherzig@gmail.com | |
| Url | https://github.com/ash-fortyfive |
| Summary | PhD researcher applying machine learning to real-world problems in computer vision, 3D graphics, and human motion synthesis. Experienced in developing end-to-end deep learning systems, from multi-view data capture and preprocessing to model training and evaluation. Focused on generative modeling and building people-centered AI for communication and expression. |
Work
-
2023.09 - Present Graduate Teaching Assistant
University of Surrey
Part of the team delivering labs for CS and EEE courses, providing lab instruction and technical mentoring.
- Covered COM1031 (Computer Logic), EEE1035 (C Programming), EEE2048 (Algorithms)
- Completed GTA training to enhance teaching, feedback, and teamwork skills
-
2022.06 - 2022.09 Summer Research Intern
University of Surrey
Research on multi-agent reinforcement learning strategies for UAV access control, with a focus on reproducibility and model efficiency.
- Reimplemented baselines from Matlab to PyTorch for reproducible experimentation
- Designed and trained deep policy networks using DQN
- Evaluated agent coordination strategies in simulated environments
-
2021.06 - 2022.06 Associate Development Engineer
Sky Group
Collaborated with an agile engineering team to develop computer vision tools for automated set-top box validation, integrating OCR pipelines into production workflows.
- Built OCR pipelines for detecting on-screen text and anomalies in video streams
- Deployed computer vision tools for regression testing in content validation workflows
- Refactored legacy systems from Python 2 to Python 3, improving stability and maintainability
- Worked within an agile scrum framework, managing project tasks with Jira and participating in daily stand-ups
Volunteer
-
2023.09 - 2024.06 Societies Chair
University of Surrey Students' Union
Oversaw the Student's Union societies, supporting over 150 student-led groups and leading monthly meetings.
-
2019.09 - 2025.06 Committee Member / Founder
University of Surrey Societies
Founded GameDev Society; held leadership roles in GameSoc and EARS societies.
Education
-
2023.09 - 2027.09 PhD
University of Surrey
Computer Vision
- Thesis Working Title: Translation and Production of Non-Manual Features for Sign Language
-
2019.09 - 2023.06 BEng (Hons)
University of Surrey
Electronic Engineering
- Graduated with First Class Honours
- Computer Vision
- Computer Graphics
- C++ and Object-Oriented Design
- Computer Algorithms and Architecture
Publications
-
2025.07.15 VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis
arXiv preprint [Accepted at ICCV Workshops]
Proposed a visual speech-driven method for generating high-fidelity 3D avatar lip motion, using a visual speech recognition model to supervise 3D Gaussian Splatting renders, boosting perceptual realism and accuracy.
Skills
| Languages & Frameworks | |
| Python | |
| PyTorch | |
| OpenCV |
| Tools | |
| Docker | |
| Git | |
| Weights & Biases | |
| LaTeX | |
| Linux | |
| SLURM |
| Specialized | |
| 3D Morphable Models | |
| Unreal Engine | |
| Neural Rendering | |
| 3DGS |
Languages
| English | |
| Professional proficiency |
| German | |
| Working proficiency |
| Dutch | |
| Working proficiency |
| Greek | |
| Working proficiency |
Interests
| Research | |
| Computer Vision | |
| 3D Graphics | |
| Human Motion Synthesis | |
| Sign Language Translation |
| Hobbies | |
| Game Development | |
| Board Games | |
| Climbing | |
| Weightlifting |
Projects
- 2025.05 - 2025.08
PokerGym: Multi-Agent Poker Environment
- Developed fully custom multi-agent environment using PettingZoo’s AECEnv API and Gymnasium integration
- Implemented full training pipeline using Proximal Policy Optimization (PPO), including reward tracking and action masking
- Simulated realistic betting, turn-taking, and side-pot resolution to support advanced strategy learning
- Designed for reproducibility and extensibility in research workflows
- 2023.09 - 2024.09
Volumetric Sign Capture System
- Designed hardware using Raspberry Pis and high-quality cameras
- Built camera synchronization modules and custom control software
- System supports multi-view capture for dataset creation used in training facial motion synthesis models
- 2022.09 - 2023.06
Marker-less Motion Capture for Signing Avatar
- Built a pipeline combining MediaPipe, custom uplift network, and Unreal Engine Metahumans
- Demonstrated real-time signing avatar driven from monocular video