Adaptive image interpolation using coupled bidirectional flow

Image interpolation is a common problem in imaging applications. However, most existing interpolation algorithms in existence suffer visually the effects of blurred edges and jagged artifacts in image to some extent. This paper presents a unified bidirectional flow process, where an inverse diffusion is performed to enhance edges along the normal directions to the isophote lines (edges), while a normal diffusion is done to remove artifacts ("jaggies") along the tangent directions. At the same time, adaptive processes such as soft edge decision, split-coupling scheme and feature-oriented diffusion coefficients ensure an effective preservation of image features such as edges, corners and textures. And then we apply above process to image interpolation. Experimental results demonstrate that our interpolation algorithm substantially improves the subjective quality of the interpolated images over conventional interpolations and relative equations.