Alan C. Bovik

TL;DR: The ETRI-LIVE Space-Time Sub-sampled Video Quality (ETRI-Live STSVQ) dataset as discussed by the authors contains 437 videos generated by applying various levels of combined space-time subsampling and video compression on 15 diverse video contents.

TL;DR: The proposed defog and visibility enhancer makes use of statistical regularities observed in foggy and fog-free images to extract the most visible information from three processed image results: one white balanced and two contrast enhanced images.

TL;DR: The Binocular Perceptual Crosstalk Predictor (BPCP) uses measurements of three complementary 3D image properties in combination with two well-known factors to make predictions of crosstalk on two-view auto-stereoscopic displays and explores a new masking phenomenon that is called duplicated structure masking, which arises from structural correlations between the original and distorted objects.

TL;DR: An accurate model for predicting the upscaling ratio applied to any natural image is developed by decomposing an input image frame using an orthogonal filter bank and locally normalizing the resulting responses, and it is shown that the local energy terms can be used to predict the upScaling ratio.

TL;DR: This work proposes a new “naturalness”-based image quality predictor for generative images that is built using a multi-stage parallel boosting system based on structural similarity features and measurements of statistical similarity.