Search

There has been an increasing number of image super-resolution (SR) algorithms proposed recently to create images with higher spatial resolution from low-resolution (LR) images. Nevertheless, how to evaluate the performance of such SR and interpolation algorithms remains an open problem. Subjective assessment methods are useful and reliable, but are expensive, time-consuming, and difficult to be embedded into the design and optimization procedures of SR and interpolation algorithms. Here we make one of the first attempts to develop an objective quality assessment method of a given resolution-enhanced image using the available LR image as a reference. Our algorithm follows the philosophy behind the natural scene statistics (NSS) approach. Specifically, we build statistical models of frequency energy falloff and spatial continuity based on high quality natural images and use the departures from such models to quantify image quality degradations. Subjective experiments have been carried out that verify the effectiveness of the proposed approach. [ABSTRACT FROM PUBLISHER]

Extensive research has been conducted relating the natural scene statistics of luminance and depth; however, very little work has been done on analyzing the statistical relationships between depth and chromatic information. In this paper, we examine and derive statistical models between disparity and both luminance and chrominance information by transforming natural images into the more perceptually relevant CIELAB color space. To demonstrate the effectiveness of these models, we further exploit them with application to Bayesian stereo algorithms. The simulation results show that incorporating the derived statistical models augments the performance of Bayesian stereo algorithms. In addition, these results also support psychophysical evidence that chromatic information can improve binocular visual processing. [ABSTRACT FROM PUBLISHER]