Hi, I'm Dimitrios, but most people, including me, prefer to call me Dimitris. I am a PhD candidate in the
Department of Computing at
Imperial College London, supervised by
Professor Stefanos Zafeiriou.
My research lies at the intersection of Machine Learning, Computer Vision, and Graphics, with a particular focus on
Digital Humans.
3D Human ModelingDiffusion ModelsVideo ModelsDistillation
Research Interests
Controllable Limited-View 3D Avatars
Reconstruction from limited-view setups, with an emphasis on single in-the-wild image inputs, using modern 3D
representations together with generative priors, and making the avatars controllable, so they can convey
realistic expressions, speech, and motion in general.
Diffusion Models
Large-scale (foundation) image diffusion models used as strong priors, and diffusion models that operate directly
on 3D representations such as meshes, with a focus on human-centric models and the applications they unlock.
Video Models
Controllable video diffusion models for human-centric tasks, driven by audio and parametric head model parameters for accurate
animation and reenactment, and their potential to be pushed toward real-time, streaming 2D avatars.
Distillation
Distilling strong 2D priors into lightweight generative models for 3D representations, so their potential carries
over to 3D generation.
PII-Free Solutions
Human data is sensitive by nature. I am interested in PII-free solutions, fine-tuning large priors on synthetic human data to
achieve realistic results without requiring real data during fine-tuning.
News
Latest first
Feb 2026Started as a Student Researcher at Google AR/VR, London!
Jun 2025Joined Meta Reality Labs, London, as a Research Scientist Intern!
@article{gerogiannis2025arc2avatar,
title={Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance},
author={Gerogiannis, Dimitrios and Papantoniou, Foivos Paraperas and Potamias, Rolandos Alexandros and Lattas, Alexandros and Zafeiriou, Stefanos},
journal={arXiv preprint arXiv:2501.05379},
year={2025}
}
@inproceedings{gerogiannis2024animateme,
title={AnimateMe: 4D facial expressions via diffusion models},
author={Gerogiannis, Dimitrios and Papantoniou, Foivos Paraperas and Potamias, Rolandos Alexandros and Lattas, Alexandros and Moschoglou, Stylianos and Ploumpis, Stylianos and Zafeiriou, Stefanos},
booktitle={European Conference on Computer Vision},
pages={270--287},
year={2024},
organization={Springer}
}
