no code implementations • ICCV 2017 • Paul Gay, Cosimo Rubino, Vaibhav Bansal, Alessio Del Bue
We show that remarkable object localisation and volumetric occupancy can be recovered by including both geometrical constraints and prior information given by objects CAD models from the ShapeNet dataset.
no code implementations • CVPR 2016 • Marco Crocco, Cosimo Rubino, Alessio Del Bue
In practice, this work can be considered as the extension of Tomasi and Kanade factorization method using objects.
no code implementations • 17 Feb 2015 • Cosimo Rubino, Marco Crocco, Alessandro Perina, Vittorio Murino, Alessio Del Bue
We present a novel method to infer, in closed-form, a general 3D spatial occupancy and orientation of a collection of rigid objects given 2D image detections from a sequence of images.