Title: Learning Object-Independent
Modes of Variation with Feature Flow Fields
Erik Miller
Abstract:
We present a unifying framework in which object-independent modes of variation
are learned from continuous-time data such as video sequences. These modes of
variation can be used as generators to produce a manifold of images of a new
object from a single example of that object. We develop the framework in the
context of a well-known example: analyzing the modes of spatial deformations of
a scene under camera movement. The method learns a close approximation to the
standard affine deformations that are expected from the geometry of the
situation, and does so in a completely unsupervised (i.e. ig-norant
of the geometry of the situation) fashion. We then demonstrate
how we have used the same framework to derive a novel data-driven model of
joint color change in images due to common lighting variations. The model
captures various phenomena (for example, contrast changes) not captured by
traditional linear color change models. Finally, we suggest other modes of
variations that are could be captured by such a framework.