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
Posted Content
Learning to Compress Videos without Computing Motion.
TL;DR: The experimental results show that the proposed compression model, which is called the MOtionless VIdeo Codec (MOVI-Codec), learns how to efficiently compress videos without computing motion and is highly competitive with, and sometimes exceeds the performance of the modern global standard HEVC codec, as measured by MS-SSIM.
Proceedings ArticleDOI
Perceptual soft thresholding using the structural similarity index
TL;DR: The visual quality of the images denoised using the proposed algorithm is shown to be higher compared to the MSE-optimal soft thresholding denoising solution, as measured by the SSIM Index.
Book ChapterDOI
22 Order statistics in image processing
Scott T. Acton,Alan C. Bovik +1 more
TL;DR: In this article, the authors discuss the application of order statistics in digital image processing and apply it to an amazing diversity of image types, which may be electromagnetic, sonic, or atomic and also dependent on the types of sensors used to capture the data.
Proceedings ArticleDOI
Foveated Analysis and Selection of Visual Fixations in Natural Scenes
TL;DR: A novel foveated analysis framework is presented, in which features were analyzed at the spatial resolution at which they were perceived, and a new algorithm is presented that selects image regions as likely candidates for fixation.
Proceedings ArticleDOI
Video Quality Model for Space-Time Resolution Adaptation
TL;DR: In this paper, a new video quality model is proposed to predict the perceptual quality of videos undergoing varying levels of spatio-temporal subsampling and compression, which leverage the fact that pristine videos obey statistical regularities that are disturbed by distortions.