A Survey of Image Statistics Relevant to Computer Graphics

Pouli, Tania; Cunningham, Douglas W.; Reinhard, Erik

doi:10.1111/j.1467-8659.2011.01900.x

Cited by 24 publications

(19 citation statements)

References 155 publications

(218 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been found that natural (smoothed) image gradient components are well modeled as following a GGD [33]. Thus, we use the parameters α and β computed by fitting the histograms of the gradient components I h and I v to the GGD model (Eq.…”

Section: Gradient Statisticsmentioning

confidence: 99%

A Feature-Enriched Completely Blind Image Quality Evaluator

Zhang

Bovik

2015

IEEE Trans. on Image Process.

935

416

View full text Add to dashboard Cite

Abstract-Existing blind image quality assessment (BIQA) methods are mostly opinion-aware. They learn regression models from training images with associated human subjective scores to predict the perceptual quality of test images. Such opinion-aware methods, however, require a large amount of training samples with associated human subjective scores and of a variety of distortion types. The BIQA models learned by opinion-aware methods often have weak generalization capability, hereby limiting their usability in practice. By comparison, opinion-unaware methods do not need human subjective scores for training, and thus have greater potential for good generalization capability. Unfortunately, thus far no opinion-unaware BIQA method has shown consistently better quality prediction accuracy than the opinion-aware methods. Here, we aim to develop an opinionunaware BIQA method that can compete with, and perhaps outperform, the existing opinion-aware methods. By integrating the features of natural image statistics derived from multiple cues, we learn a multivariate Gaussian model of image patches from a collection of pristine natural images. Using the learned multivariate Gaussian model, a Bhattacharyya-like distance is used to measure the quality of each image patch, and then an overall quality score is obtained by average pooling. The proposed BIQA method does not need any distorted sample images nor subjective quality scores for training, yet extensive experiments demonstrate its superior quality-prediction performance to the state-of-the-art opinion-aware BIQA methods. The MATLAB source code of our algorithm is publicly available at www.comp.polyu.edu.hk/∼cslzhang/IQA/ILNIQE/ILNIQE.htm.Index Terms-Blind image quality assessment, natural image statistics, multivariate Gaussian.

show abstract

Section: Gradient Statisticsmentioning

confidence: 99%

A Feature-Enriched Completely Blind Image Quality Evaluator

Zhang

Bovik

2015

IEEE Trans. on Image Process.

935

416

View full text Add to dashboard Cite

show abstract

“…Natural illumination exhibits statistical regularities that largely coincide with those found for images of natural environments (DLAW01), (PCR10). In particular, the joint and marginal wavelet coefficient distributions, harmonic spectra, and directional derivative distributions are similar.…”

Section: Perceptual Frameworkmentioning

confidence: 51%

Perception-based image editing

Gutiérrez

2009

2009 XXII International Symposium on Information, Communication and Automation Technologies

View full text Add to dashboard Cite

2To María Jesús, for so many reasons that I would need to write another book just to thank her.To my parents for giving me only thing than no one can ever take from you, education.To my friends and family because, in spite of my increasing computer graphics geekness over the last years, they still come to see movies with me, daring even to ask what was my last paper about.To Diego, for telling me that what I really wanted was to become a PhD.And to the one who just arrived, Juan. Lucky you. You were spared from hours of thesis-related ramblings.i Acknowledgments

show abstract

“…It has been successfully applied to practical applications of shape modelling [25], image segmentation [26][27][28], image reconstruction [29,30], motion analysis [31], bias correction [32,33], image registration [34], image retrieval [35,36] and deconvolution [37,38] in the fields of medial imaging and medical image analysis. In addition, it has also been used in a large variety of applications in the field of computer vision, including face recognition [39], image restoration [40], image denoising, deblurring, superresolution and object recognition [41][42][43][44][45][46][47][48].…”

Section: Sparsity Priormentioning

confidence: 99%