Lorenzo Porzi

Research Engineer

I am a Research Engineer at Facebook, working from Zurich with the Spatial Computing group. My main research interests are semantic and 3D understanding of images, with special focus on street level scenes. Before joining Facebook I tackled similar problems while working as a Research Scientist at Mapillary. I received my PhD in Computer Vision from the University of Perugia, Italy, where I did research in augmented reality and deep learning.


Semantic segmentation, panoptic segmentation, 3D object detection

Related Links

Google Scholar

Latest Publications

CVPR - June 18, 2021

Improving Panoptic Segmentation at All Scales

Lorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder

ECCV - August 22, 2020

Improving Optical Flow on a Pyramid Level

Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi, Arno Knapitsch, Thomas Pock, Peter Kontschieder

ECCV - August 22, 2020

Towards Generalization Across Depth for Monocular 3D Object Detection

Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi, Elisa Ricci, Peter Kontschieder