Summary: J. H. Shin, J. K. Paik, J. R. Price, and M. A. Abidi, "Adaptive regularized image interpolation using data fusion and steerable constraints,"
Proc. SPIE Visual Comm., Image Proc., Vol. 4310, pp. 798-809, San Jose, CA, January 2001.119
adequate LR image frames to higher resolution restoration, but also construct a general framework based on image
fusion toward the problem of multiframe image interpolation.
Many algorithms have been proposed to improve the resolution of images. Conventional interpolation algorithms,
such as zero-order or nearest neighbor, bilinear, cubic B-spline, and the DFT-based interpolation, can be classified
by basis functions, and they focus on just enlargement of image.2,6,7
Those algorithms have been developed under
assumption that there are no mixture among adjacent pixels in the imaging sensor, no motion blur due to finite
shutter speed of the camera, no isotropic blur due to out-of-focus, and no aliasing in the process of sub-sampling.
Since the assumptions mentioned above are not satisfied in general low-resolution imaging systems, it is not easy to
restore the original high-resolution image by using the conventional interpolation algorithms.
In order to improve the performance of the above mentioned algorithms, a spatially adaptive cubic interpolation
method has been proposed in.8
Although it can preserve a number of directional edges in the interpolation process, it
is not easy to restore original high frequency components which are lost in the sub-sampling process. As a alternative,
multi-frame interpolation techniques which use sub-pixel motion information have been proposed in.925
It is well-known that image interpolation is an ill-posed problem. More specifically, we regard a sub-sampling
process as a general image degradation process. Then the regularized image interpolation is to find the inverse solution
defined by the image degradation model subject to a priori constraint.12,13