Alan C. Bovik

TL;DR: This paper analyzes five multi-resolution-based image fusion methods in regards to several common distortions, including blur, white noise, JPEG compression, and non-uniformity and proposes an opinion-aware fused image quality analyzer, whose relative predictions with respect to other state-of-the-art models correlate better with human perceptual evaluations than competing methods.

TL;DR: A perceptual fog density prediction model based on natural scene statistics and “fog aware” statistical features, which can predict the visibility in a foggy scene from a single image without reference to a corresponding fogless image, without side geographical camera information, and without training on human-rated judgments.

TL;DR: In this paper, a model relating the spatially varying instantaneous frequency of the image texture to the surface texture, to the orientation of the surface, and to the parameters of the imaging system is presented.

TL;DR: A full-reference video quality assessment framework that integrates analysis of space–time slices (STSs) with frame-based image quality measurement (IQA) to form a high-performance video quality predictor is developed.

TL;DR: Algorithms that measure differences between the entropies of wavelet coefficients of reference and distorted images are designed, each differing in the amount of data on which information change is predicted and ranging from almost full reference to almost no reference.