no code implementations • 19 Jan 2023 • Alwyn Mathew, Ludovic Magerand, Emanuele Trucco, Luigi Manfredi
We propose a novel multi-task model that simultaneously predicts dense depth and lumen segmentation with an ensemble of deep networks.
no code implementations • ICCV 2017 • Ludovic Magerand, Alessio Del Bue
This paper presents a solution to the Projective Structure from Motion (PSfM) problem able to deal efficiently with missing data, outliers and, for the first time, large scale 3D reconstruction scenarios.