Image and Video Inpainting
Electrical and Computer Engineering,
University of Minnesota
Wednesday, January 23, 2002 13:00-14:00,
Inpainting, the technique of modifying an image in an undetectable form,
is as ancient as art itself. The goals and applications of inpainting are
numerous, from the restoration of damaged paintings and photographs to the
removal/replacement of selected objects.
Inspired in part by the work of Masnou and Morel and that of
Nitzberg and Mumford, we have developed a number of
novel algorithms for digital inpainting of still and video color images.
After the user selects the regions to be
inpainted, the algorithms automatically fill-in these regions with
the information surrounding them. The filling-in is done via
high order PDE's or coupled PDE's
in such a way that isophote lines arriving at the regions boundaries are
completed inside. In contrast with previous approaches, the techniques
developed do not require the user to specify where the novel information
comes from. This is automatically done (and in a fast way),
thereby allowing to simultaneously fill-in numerous regions containing
completely different structures and surrounding backgrounds.
In addition, no limitations are imposed on the topology of the region to be
inpainted. In this talk I will present the models,
the underlying theory and connections with
Navier-Stokes, and show applications in numerous areas.
We will also describe the application of this work to image compression
and wireless image transmission.
Room 145, NIST North (820)
Wednesday, January 23, 2002 11:00-12:00,
Contact: A. S. Carasso
Note: Visitors from outside NIST must contact
Robin Bickel; (301) 975-3668;
at least 24 hours in advance.