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. In more detail, I work on methods for 3D facial reconstruction from limited-view setups (as little as a single image) to create realistic avatars using the advances in both 3D representations (3D Gaussian Splats) and generative models (Diffusion Models). My efforts are also centered around making these avatars controllable so they can convey expressions and speech and animation in general. I am also very interested in large-scale diffusion models, especially human-centric foundation models and their multiple use cases in both the 2D and 3D domain. Prior to beginning my PhD, I graduated with a Diploma (BSc+MEng) in Computer Science from the Computer Engineering and Informatics Department at the University of Patras , where I was advised by Professor Emmanouil Z. Psarakis for my thesis.

Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance CVPR
Dimitrios Gerogiannis , Foivos Paraperas Papantoniou , Rolandos Alexandros Potamias , Alexandros Lattas , Stefanos Zafeiriou
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
BibTeX
@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} }

AnimateMe: 4D Facial Expressions via Diffusion Models ECCV
Dimitrios Gerogiannis , Foivos Paraperas Papantoniou , Rolandos Alexandros Potamias , Alexandros Lattas , Stylianos Moschoglou , Stylianos Ploumpis , Stefanos Zafeiriou
European Conference on Computer Vision (ECCV), 2024
BibTeX
@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} }