Published multiple papers including but not limited to EgoTempo Benchmark, ACED, VICT, Emuru; listed as a contributor to the Gemini 2.5 report; LIME was selected for an oral presentation at WACV2025; UIP2P accepted at ICCV25; several projects such as TouchSDF, TextMesh, NeRF-GAN Distillation, LatentSwap3D were accepted by various conferences or journals.
Research Experience
Works as Research Scientist Manager at Google Zurich; previously a postdoc researcher at the Computer Vision Lab, University of Bologna.
Education
Received a PhD in Computer Science and Engineering from the University of Bologna in April 2019, with a focus on deep learning solutions for product detection and recognition in retail environments and depth estimation from stereo and monocular cameras; supervised by Professor Luigi Di Stefano. Previously, he was a postdoc at the Computer Vision Lab of the University of Bologna.
Background
Researcher in computer vision and deep learning. Currently working at Google Zurich, leading a small team focused on fundamental research and transforming research into production. Interested in multimodal learning, generative models for images, and complex text understanding tasks.
Miscellany
Besides his professional achievements, enjoys photography and maintains a rarely updated Flickr account.