There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

We propose a natural scene statistic-based distortion-generic blind/no-reference (NR) image quality assessment (IQA) model that operates in the spatial domain. The new model, dubbed blind/referenceless image spatial quality evaluator (BRISQUE) does not compute distortion-specific features, such as ringing, blur, or blocking, but instead uses scene statistics of locally normalized luminance coefficients to quantify possible losses of “naturalness” in the image due to the presence of distortions, thereby leading to a holistic measure of quality. The underlying features used derive from the empirical distribution of locally normalized luminances and products of locally normalized luminances under a spatial natural scene statistic model. No transformation to another coordinate frame (DCT, wavelet, etc.) is required, distinguishing it from prior NR IQA approaches. Despite its simplicity, we are able to show that BRISQUE is statistically better than the full-reference peak signal-to-noise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms. BRISQUE has very low computational complexity, making it well suited for real time applications. BRISQUE features may be used for distortion-identification as well. To illustrate a new practical application of BRISQUE, we describe how a nonblind image denoising algorithm can be augmented with BRISQUE in order to perform blind image denoising. Results show that BRISQUE augmentation leads to performance improvements over state-of-the-art methods. A software release of BRISQUE is available online: http://live.ece.utexas.edu/research/quality/BRISQUE_release.zip for public use and evaluation.

/pdf/no-reference-image-quality-assessment-in-the-spatial-domain-2mnlvf25ig.pdf

No-Reference Image Quality Assessment in the Spatial Domain

An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art “general purpose” no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of training examples and corresponding human opinion scores. However we have recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed without any exposure to distorted images. Thus, it is “completely blind.” The new IQA model, which we call the Natural Image Quality Evaluator (NIQE) is based on the construction of a “quality aware” collection of statistical features based on a simple and successful space domain natural scene statistic (NSS) model. These features are derived from a corpus of natural, undistorted images. Experimental results show that the new index delivers performance comparable to top performing NR IQA models that require training on large databases of human opinions of distorted images. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.

/pdf/making-a-completely-blind-image-quality-analyzer-4rsald8tn3.pdf

Making a “Completely Blind” Image Quality Analyzer

On robust estimation of the location parameter

This paper presents a deep automatic colorization approach which avoids any manual intervention. Recently Generative Adversarial Network (GANs) approaches have proven their effectiveness for image colorization tasks. Inspired by GANs methods, we propose a novel colorization model that produces more realistic quality results. The model employs an additional discriminator which works in the feature domain. Using a feature discriminator, our generator produces structural high-frequency features instead of noisy artifacts. To achieve the required level of details in the colorization process, we incorporate non-adversarial losses from recent image style transfer techniques. Besides, the generator architecture follows the general shape of U-Net, to transfer information more effectively between distant layers. The performance of the proposed model was evaluated quantitatively as well as qualitatively with places365 dataset. Results show that the proposed model achieves more realistic colors with less artifacts compared to the state-of-the-art approaches.

Automatic Image Colorization based on Multi-Discriminators Generative Adversarial Networks

Il s'agit d'evaluer la pertinence de modeles probabilistes lineaires et circulaires pour la description de textures directionnelles, en vue de leur classification ou de leur synthese. Dans un schema multi-echelle mettant en œuvre une decomposition pyramidale orientee, nous avons associe des modeles lineaires et circulaires pour la description parametrique des modules et orientations issus de l'analyse des sous bandes complexes resultant de la decomposition. Dans un cadre experimental d'indexation de textures, nous montrons qu'il est pertinent d'associer a une modelisation des modules, non seulement la prise en compte mais aussi la modelisation des orientations. Nous comparons plusieurs modeles probabilistes circulaires et evaluons l'importance du choix de la metrique pour la manipulation de ces modeles.

http://documents.irevues.inist.fr/bitstream/handle/2042/29063/peron_535.pdf;sequence=1

Modèles linéaires et circulaires pour la caractérisation de textures orientées.

Estimation récursive du champ d’orientation par reconstruction d’hypersurfaces et changement d’espace

This special issue of the Journal of the Optical Society of America A (JOSA A) is devoted to the wide array of French researchers from universities and state research organisms, offering them the opportunity to share and showcase their current research in the fields of optics and imaging sciences to the global community.

Classical optics in France: introduction.

In this paper, a new framework is presented for the quantitative evaluation of the performance of appearance models composed of an object descriptor and a similarity measure in the context of object tracking. The evaluation is based on natural videos, and takes advantage of existing ground-truths from object tracking benchmarks. The proposed metrics evaluate the ability of an appearance model to discriminate an object from the clutter. This allows comparing models which may use diverse kinds of descriptors or similarity measures in a principled manner. The performances measures can be global, but time-oriented performance evaluation is also presented. The insights that the proposed framework can bring on appearance models properties with respect to tracking are illustrated on natural video data.

Yannick Berthoumieu

Papers

Automatic Image Colorization based on Multi-Discriminators Generative Adversarial Networks

Modèles linéaires et circulaires pour la caractérisation de textures orientées.

Estimation récursive du champ d’orientation par reconstruction d’hypersurfaces et changement d’espace

Classical optics in France: introduction.

Evaluating descriptors performances for object tracking on natural video data