A
Alan C. Bovik
Researcher at University of Texas at Austin
Publications - 872
Citations - 120104
Alan C. Bovik is an academic researcher from University of Texas at Austin. The author has contributed to research in topics: Image quality & Video quality. The author has an hindex of 102, co-authored 837 publications receiving 96088 citations. Previous affiliations of Alan C. Bovik include University of Illinois at Urbana–Champaign & University of Sydney.
Papers
More filters
Proceedings ArticleDOI
Look-up-table based DCT domain inverse motion compensation
Shizhong Liu,Alan C. Bovik +1 more
TL;DR: A look-up-table (LUT) based method for DCT domain inverse motion compensation is proposed by modeling the statistical distribution of the DCT coefficients in typical images and video sequences to save more than 50% of the computing time based on experimental results.
Proceedings ArticleDOI
Non-stationary texture segmentation using an AM-FM model
TL;DR: This work uses a multidimensional AM-FM representation for the texture and provides the FM features to an SOFM-LVQ neural network system that performs the segmentation, and shows how these eigenvalues capture the non-stationary structure of a texture.
Journal ArticleDOI
Estimating the Resize Parameter in End-to-end Learned Image Compression
TL;DR: A search-free resizing framework that can further improve the rate-distortion tradeoff of recent learned image compression models is described, which suggests that “compression friendly” downsampled representations can be quickly determined during encoding by using an auxiliary network and differentiable image warping.
Journal ArticleDOI
Least-squares order statistic filters with coefficient censoring
Laith Naaman,Alan C. Bovik +1 more
TL;DR: In this paper, the effect of coefficient censoring on the noise smoothing performance of order statistic (OS) filters is considered, and it is shown that coefficientcensoring leads to increased robustness against outlying or impulsive noise occurrences relative to uncensored filters.
Journal ArticleDOI
Blind S3D image quality prediction using classical and non-classical receptive field models
TL;DR: A novel no-reference image quality assessment model for stereoscopic 3D images that is inspired by functional receptive field models of perceptual mechanisms in primary visual cortex, and exhibits good performance across the datasets suggesting that it is general, and it has relatively low complexity.