Invited Speaker

Invited speaker place

 

Francesc Moreno-Noguer

Francesc Moreno-Noguer
Associate Researcher
Institut de Robòtica i Informàtica Industrial (CSIC-UPC)
Barcelona, Spain

Bio-CV

Francesc Moreno-Noguer received the MSc degrees in industrial engineering and electronics from the Technical University of Catalonia (UPC) and the Universitat de Barcelona in 2001 and 2002, respectively, and the PhD degree from UPC in 2005. From 2006 to 2008, he was a postdoctoral fellow at the computer vision departments of Columbia University and the Ecole Polytecnique Fédérale de Lausanne. In 2009, he joined the Institut de Robòtica i Informàtica Industrial in Barcelona as an associate researcher of the Spanish Scientific Research Council. His research interests include retrieving rigid and nonrigid shape, motion, and camera pose from single images and video sequences, with applications to both robotics and medical imaging. He received UPC’s Doctoral Dissertation Extraordinary Award for his work and an outstanding reviewer award at ECCV’12 and CVPR’14. Further information can be found at http://www.iri.upc.edu/people/fmoreno/.

Monocular 3D detection of rigid and non-rigid shapes

In this talk, I will first present an approach to the PnP problem, the estimation of the pose of a calibrated camera from n point correspondences between an image and a 3D model of a rigid object, whose computational complexity grows linearly with n. Our central idea is to express the 3D points as a weighted sum of four virtual control points. The problem then reduces to estimating the coordinates of these control points in the camera coordinate system, which can be done in O(n) using simple linearization techniques. I will then show how an algebraic outlier rejection scheme can be introduced within the computation of the pose, without the need to resort to RANSAC-based strategies.

In the second part of the talk I will show how the same linear formulations can be extended to retrieving the shape of 3D deformable objects. However, since monocular non-rigid reconstruction is severely under-constrained we will have to consider additional constraints, either based on local rigidity (to reconstruct deformable and inextensible surfaces), or based on shading coherence (to reconstruct deformable and stretchable surfaces). Finally I will discuss the major limitations of these linear formulations and propose a novel and alternative stochastic exploration strategy. I will present results both for non-rigid shape and human pose recovery.