Three examples of inpainting using the Navier-Stokes based method
from
M. Bertalmio, A. Bertozzi, and G. Sapiro, CVPR 2001.
The idea
Image inpainting involves filling in part of an image or
video
using information from the surrounding area. Applications
include the restoration of damaged photographs and movies
and the removal
of selected objects. In this paper, we introduce a
class of automated methods for digital inpainting.
The approach uses ideas from classical fluid dynamics to
propagate
isophote lines continuously from the exterior into the
region to be inpainted.
The main idea is to think of the image intensity as a
`stream function' for a
two-dimensional incompressible
flow. The Laplacian of the image intensity plays the role of
the vorticity of
the fluid; it is transported into
the region to be inpainted by a vector field defined by the
stream function.
The resulting algorithm is designed to continue isophotes
while matching
gradient vectors at the boundary of the inpainting region.
The method is directly based on the Navier-Stokes equations
for fluid
dynamics, which has the immediate advantage of
well-developed
theoretical and numerical results.
This is a new approach for introducing ideas from
computational fluid dynamics into
problems in computer vision and image analysis.
Move the cursor onto the image to see the NS restoration.
Inpainting of stills
Frame-by-frame video inpainting
Move the cursor onto the video image to see the restored video.
The foreman video overwritten with red lettering.
Super-resolution
Super resolution of one of the eyes from this photograph.
The left shows a section of an image magnified 9 times.
The middle image is modified by standard bicubic interpolation.
The right image is the result of Navier-Stokes inpainting performed
by fixing pivot points in the middle of the cells and evolving all other pixels.
Computations performed by M. Bertalmio. Cool html tricks thanks to Matt Matthews.