cv

Applied Scientist Intern

Amazon, DE

Visiting Researcher

École Polytechnique, FR

Text-to-Motion Generation with Diffusion Models.

Visiting Researcher

Max Planck Institute, DE

Semantic Control for Virtual Humans.

Research Associate

University of Cyprus, CY

Stylised 3D Human Motion Synthesis and Control - ITN CLIPE Project.

Casual Teaching Assistant

University of Bath, UK

PhD

University of Cyprus, CY

Computer Science

• Visual Computing
• Computer Graphics
• Object Oriented Programming

MSc

University of Bath, UK

Data Science

• Applied Data Science
• Machine Learning
• Deep Learning
• Reinforcement Learning
• Statistics

BSc

University of Bath, UK

Mathematics

• Probability and Statistics
• Mathematical Methods
• Optimal Control
• Mathematical Biology
• Operational Research

The Bath Award

University of Bath

The Bath Award gives students the chance to showcase to potential employers the skills they have developed through a range of extra-curricular activities including volunteering, paid work and mentoring.

LexiCrowd: A Learning Paradigm towards Text to Behaviour Parameters for Crowds

Eurographics CLIWEG Workshop

Creating believable virtual crowds, controllable by high-level prompts, is essential to creators for trading-off authoring freedom and simulation quality. The flexibility and familiarity of natural language in particular, motivates the use of text to guide the generation process. Capturing the essence of textually described crowd movements in the form of meaningful and usable parameters, is challenging due to the lack of paired ground truth data, and inherent ambiguity between the two modalities. In this work, we leverage a pretrained Large Language Model (LLM) to create pseudo-pairs of text and behaviour labels. We train a variational auto-encoder (VAE) on the synthetic dataset, constraining the latent space into interpretable behaviour parameters by incorporating a latent label loss. To showcase our model’s capabilities, we deploy a survey where humans provide textual descriptions of real crowd datasets. We demonstrate that our model is able to parameterise unseen sentences and produce novel behaviours, capturing the essence of the given sentence; our behaviour space is compatible with simulator parameters, enabling the generation of plausible crowds (text-to-crowds). Also, we conduct feasibility experiments exhibiting the potential of the output text embeddings in the premise of full sentence generation from a behaviour profile.

Pose Representations for Deep Skeletal Animation.

Computer Graphics Forum

In this work, we address the fundamental problem of finding a robust pose representation for motion, suitable for deep skeletal animation, one that can better constrain poses and faithfully capture nuances correlated with skeletal characteristics. We propose a novel representation based on dual quaternions and show experimentally superior results in terms of training convergence and perceived realism of generated motions.

Virtual Dance Museum: the Case of Greek/Cypriot Folk Dancing.

Eurographics Association

In this paper, we have designed and developed a virtual dance museum. The users can view and interact with the archived data using advanced 3D character visualization in three ways: via an online 3D virtual environment; in virtual reality using headset; and in augmented reality, where the 3D characters can co-inhabit the real world.