IPAB Seminar - 17/07/19

Félix Escalona

With the emergence of low cost 3D sensors, the focus is moving towards the

recognition and scene understanding of tridimensional data. This     

kind of representation is really challenging in terms of computation,

and it needs the development of new strategies and algorithms to be       

handled and interpreted. In this work, we propose NurbsNet, a novel

approach for 3D object classification based on local similarities with      

free form surfaces modeled as NURBS.

John Alejandro Castro Vargas

Hand pose recognition from point cloud by means of graph convolutional networks.

The talk will present initial results obtained from a synthetic dataset generated with UnrealEngine.