3D reconstruction from images has been a tremendous success-story of computer
vision, with city-scale reconstruction now a reality. However, these successes
apply almost exclusively in a static world, where the only motion is that of
the camera. Even with the advent of real time depth cameras, full 3D modelling
of dynamic scenes lags behind the rigid-scene case, and for many objects of
interest (e.g. animals moving in natural environments), depth sensing remains
challenging. In this talk, I will discuss a range of recent work in the
modelling of nonrigid real-world 3D shape from 2D images, for example building
generic animal models from internet photo collections. While the state of the
art depends heavily on dense point tracks from textured surfaces, it is rare
to find suitably textured surfaces: most animals are limited in texture (think
of dogs, cats, cows, horses, ...). I will show how this assumption can be
relaxed by incorporating the strong constraints given by the object's
silhouette.

bio:

Andrew Fitzgibbon is a principal researcher at Microsoft Research, Cambridge,
UK. His research interests are in the intersection of computer vision and
computer graphics, with excursions into neuroscience. Recent papers have been
on models of nonrigid motion, human 3D perception,large-scale image search, and
nonlinear optimization.

He has co-authored ``best papers'' at ICCV (2x), CVPR (2x), ISMAR (2x), and
BMVC (3x), and software he wrote won an Engineering Emmy Award in 2002 for
significant contributions to the creation of complex visual effects. He studied
at University College Cork, at Heriot-Watt university, and received his PhD
from Edinburgh University in 1997. Until June 2005 he held a Royal Society
University Research Fellowship at Oxford University's Department of Engineering
Science.