A Self-Adapting Bilateral Total Variation Technology for Image Super-Resolution Reconstruction

Super-resolution image reconstruction has recently drawn considerable attention within the research area. For some special-purpose imaging devices such as medical imaging, remote sensor imaging and video capturing, the acquired images cannot often achieve a higher resolution because of the limitation of imaging mechanism and imaging sensor. Super-resolution image reconstruction methods attempt to create a single high resolution and high quality image from multiple low resolution observations (or a video sequence) degraded by warping, blurring, noise and aliasing. So far, existing super-resolution methods are all confronted with the problems of slow convergence and expensive computation. To satisfy the requirement of real occasion applications, an effective super-resolution reconstruction algorithm is built upon the MAP framework. In the proposed algorithm, the conception of self-adapting weight coefficients matrix (SWCM) in super-resolution technology is proposed. And a new method on super-resolution based on self-adapting bilateral total variation is given. The method takes into account respective characteristic about each LR image. It can not only sharpen edges but also help to suppress noise in the estimated HR image. The super-resolution reconstruction model and iterative scheme are developed to get the more accurate image. Experimental results using both real and synthetic data show the effectiveness of the proposed algorithm.