Description

In the last decade, many approaches have been proposed to retrieve the 3D reconstruction of dynamic objects from a sequence of monocular images [1,2,3]. Most of them have in common that they can only recover a part of the surface which is observed. In this project, we will analyze the 3D reconstruction of closed surfaces from objects with volume [4,5], such as animals, faces, bodies, etc. To this end, we first review template-based and template-free methods, and then we propose a novel technique where different type of priors is exploited. This master thesis will be carried on in the Institut de Robòtica i Informàtica Industrial, at the Universitat Politècnica de Catalunya (under direction of Dr. Antonio Agudo and Dr. Francesc Moreno).


Requisites:

Candidates with a background in computer vision and good programming skills (Matlab/C++) are particularly encouraged to apply.


For additional information, please contact Dr. Antonio Agudo at aagudo@iri.upc.edu or Dr. Francesc Moreno at fmoreno@iri.upc.edu


[1] A. Agudo, F. Moreno-Noguer, B. Calvo and J.M.M. Montiel. Sequential Non-Rigid Structure from Motion using Physical Priors. In PAMI, 2016.

[2] R. Garg, A. Roussos, and L. Agapito. Dense variational reconstruction of non-rigid surfaces from monocular video. In CVPR, 2013.

[3] Y. Dai, H. Li and M. He. A simple prior-free method for non-rigid structure from motion factorization. In CVPR, 2012.

[4] S. Vicente and L. Agapito. Balloon shapes: reconstruction and deforming objects with volume from images. In 3DV, 2013.

[5] S. Parashar, D. Pizarro, A. Bartoli and T. Collins. As-Rigid-As-Possible Volumetric Shape-from-Template. In ICCV, 2015.

The work is under the scope of the following projects:

• RobInstruct: Instructing robots using natural communication skills (web)