Luigi Sigillo
Scholar

Luigi Sigillo

Google Scholar ID: woqY-ugAAAAJ
PhD Candidate in ICT, Sapienza Univerisity of Rome
Generative ModelsGenerative AIComputer VisionDeep Learning
Citations & Impact
All-time
Citations
90
 
H-index
7
 
i10-index
5
 
Publications
12
 
Co-authors
6
list available
Resume (English only)
Academic Achievements
  • Papers published: 'Generalizing Medical Image Representations via Quaternion Wavelet Networks' accepted at Neurocomputing; 'Quaternion Wavelet-Conditioned Diffusion Models for Image Super-Resolution' accepted at IJCNN 2025; 'Metadata, Wavelet, and Time Aware Diffusion Models for Satellite Image Super Resolution' accepted at 3rd ML4RS Workshop - ICLR 2025; 'GRAM: Gramian Multimodal Representation Learning and Alignment' accepted at ICLR 2025. Successfully defended his PhD thesis.
Research Experience
  • During his doctoral studies, he held a visiting researcher position at the Visual Understanding and Generation (VUG) Lab, School of Computing and Information Systems, SMU, working with Professor Shengfeng He; before starting the PhD, he worked as a full-time Machine Learning Engineer at omninext.
Education
  • Ph.D. in Information and Communication Technologies from Sapienza University of Rome, supervised by Professor Danilo Comminiello; MSc in Computer Science Engineering from Sapienza University of Rome; BSc in Computer Science Engineering from Roma Tre University.
Background
  • Research Interests: Generative deep learning, with a particular emphasis on diffusion models applied to various types of imagery, including aerial and medical images; computer vision and multimodal representation learning.
Miscellany
  • The website is powered by Jekyll with al-folio theme, hosted by GitHub Pages.