Luigi Sigillo

prof_pic.png

Hello there👋, I am Luigi Sigillo, I recently earned my Ph.D. 🎓 in Information and Communication Technologies (ICT) from Sapienza University of Rome where I was a member👨‍🔬 of the ISPAMM Lab, supervised by Professor Danilo Comminiello.

My main research focus is generative deep learning 🧠, with a particular emphasis on diffusion models 🌫️ applied to various types of imagery 🖼️, including aerial 🛰️ and medical 🏥 images. More broadly, I’m interested in computer vision 👁️ and multimodal representation learning 🔀.

During my doctoral studies I held a visiting researcher 🧳 at the Visual Understanding and Generation (VUG) Lab at the School of Computing and Information Systems, SMU, working with Professor Shengfeng He.

Before starting the PhD, I first completed the BSc at Roma Tre University and the MSc at Sapienza University Of Rome, both in Computer Science Engineering 🎓, and then worked as a full time Machine Learning Engineer 👨‍💻 for omninext.

news

Sep 19, 2025 I successfully defended my PhD thesis, marking the completion of this incredible journey.
Apr 06, 2025 “Generalizing Medical Image Representations via Quaternion Wavelet Networks” has been accepted at Neurocomputing !
Mar 31, 2025 “Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution” has been accepted at IJCNN 2025 see you in Rome!
Mar 03, 2025 “Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution” has been accepted at 3rd ML4RS Workshop - ICLR 2025 see you in Singapore!
Jan 20, 2025 “GRAM: Gramian Multimodal Representation Learning and Alignment” has been accepted at ICLR 2025 see you in Singapore!