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 opinion-unaware 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 / $\sim $ cslzhang/IQA/ILNIQE/ILNIQE.htm.

A Feature-Enriched Completely Blind Image Quality Evaluator

Color science is a multidisciplinary field with broad applications in industries such as digital imaging, coatings and textiles, food, lighting, archiving, art, and fashion. Accurate definition and measurement of color appearance is a challenging task that directly affects color reproduction in such applications. Color Appearance Models addresses those challenges and offers insight into the preferred solutions. Extensive research on the human visual system (HVS) and color vision has been performed in the last century, and this book contains a good overview of the most important and relevant literature regarding color appearance models.

https://www.spiedigitallibrary.org/journals/Journal-of-Electronic-Imaging/volume-23/issue-2/029901/Color-Appearance-Models/10.1117/1.JEI.23.2.029901.pdf

Color Appearance Models

Neural Style Transfer has shown very exciting results enabling new forms of image manipulation. Here we extend the existing method to introduce control over spatial location, colour information and across spatial scale. We demonstrate how this enhances the method by allowing high-resolution controlled stylisation and helps to alleviate common failure cases such as applying ground textures to sky regions. Furthermore, by decomposing style into these perceptual factors we enable the combination of style information from multiple sources to generate new, perceptually appealing styles from existing ones. We also describe how these methods can be used to more efficiently produce large size, high-quality stylisation. Finally we show how the introduced control measures can be applied in recent methods for Fast Neural Style Transfer.

/pdf/controlling-perceptual-factors-in-neural-style-transfer-zn37ye7zy5.pdf

Controlling Perceptual Factors in Neural Style Transfer

This article details two approaches to compute barycenters of measures using 1-D Wasserstein distances along radial projections of the input measures. The first method makes use of the Radon transform of the measures, and the second is the solution of a convex optimization problem over the space of measures. We show several properties of these barycenters and explain their relationship. We show numerical approximation schemes based on a discrete Radon transform and on the resolution of a non-convex optimization problem. We explore the respective merits and drawbacks of each approach on applications to two image processing problems: color transfer and texture mixing.

/pdf/sliced-and-radon-wasserstein-barycenters-of-measures-s297t9q7hs.pdf

Sliced and Radon Wasserstein Barycenters of Measures

We live in a dynamic visual world where the appearance of scenes changes dramatically from hour to hour or season to season. In this work we study "transient scene attributes" -- high level properties which affect scene appearance, such as "snow", "autumn", "dusk", "fog". We define 40 transient attributes and use crowdsourcing to annotate thousands of images from 101 webcams. We use this "transient attribute database" to train regressors that can predict the presence of attributes in novel images. We demonstrate a photo organization method based on predicted attributes. Finally we propose a high-level image editing method which allows a user to adjust the attributes of a scene, e.g. change a scene to be "snowy" or "sunset". To support attribute manipulation we introduce a novel appearance transfer technique which is simple and fast yet competitive with the state-of-the-art. We show that we can convincingly modify many transient attributes in outdoor scenes.

Transient attributes for high-level understanding and editing of outdoor scenes

Extended papers from NPAR 2010: Progressive color transfer for images of arbitrary dynamic range

Image manipulation takes many forms. A powerful approach involves image adjustment by example. To make color edits more intuitive, the intelligent transfer of a user-specified target image's color palette can achieve a multitude of creative effects, provided the user is supplied with a small set of straightforward parameters. We present a novel histogram reshaping technique which allows significantly more control than previous methods. Given that the user is free to chose any image as the target, the process of steering the algorithm becomes artistic. Moreover, we show for the first time that creative tone reproduction can be achieved by matching a high dynamic range image against a low dynamic range target.

Progressive histogram reshaping for creative color transfer and tone reproduction

Managing the appearance of images across different display environments is a difficult problem, exacerbated by the proliferation of high dynamic range imaging technologies. Tone reproduction is often limited to luminance adjustment and is rarely calibrated against psychophysical data, while color appearance modeling addresses color reproduction in a calibrated manner, albeit over a limited luminance range. Only a few image appearance models bridge the gap, borrowing ideas from both areas. Our take on scene reproduction reduces computational complexity with respect to the state-of-the-art, and adds a spatially varying model of lightness perception. The predictive capabilities of the model are validated against all psychophysical data known to us, and visual comparisons show accurate and robust reproduction for challenging high dynamic range scenes.

Calibrated image appearance reproduction

Colour transfer algorithms aim to apply a colour palette, mood or style from one image to another, operating either in a threedimensional colour space, or splitting the problem into three simpler one-dimensional problems. The latter class of algorithms simply treats each of the three dimensions independently, whether justified or not. Although they rarely introduce spatial artefacts, the quality of the results depends on how the problem was split into three sub-problems, i.e. which colour space was chosen. Generally, the assumption is made that a decorrelated colour space would perform best, as decorrelation makes the three colour channels semi-independent (decorrelation is a weaker property than independence). However, such spaces are only decorrelated for well-chosen image ensembles. For individual images, this property may not hold. In this work, the connection between the natural statistics of colour images and the ability of existing colour transfer algorithms to produce plausible results is investigated. This work aims to provide a better understanding of the performance of different colour spaces in the context of colour transfer.

/pdf/colour-spaces-for-colour-transfer-1m2lc5yf2g.pdf

Colour spaces for colour transfer

Color mapping or color transfer methods aim to recolor a given image or video by deriving a mapping between that image and another image serving as a reference. This class of methods has received considerable attention in recent years, both in academic literature and in industrial applications. Methods for recoloring images have often appeared under the labels of color correction, color transfer or color balancing, to name a few, but their goal is always the same: mapping the colors of one image to another. In this report, we present a comprehensive overview of these methods and offer a classification of current solutions depending not only on their algorithmic formulation but also their range of applications. We discuss the relative merit of each class of techniques through examples and show how color mapping solutions can and have been applied to a diverse range of problems.

Tania Pouli

Papers

Extended papers from NPAR 2010: Progressive color transfer for images of arbitrary dynamic range

Progressive histogram reshaping for creative color transfer and tone reproduction

Calibrated image appearance reproduction

Colour spaces for colour transfer

A Survey of Color Mapping and its Applications