Perceptual color correction through variational techniques

Learning Enriched Features for Fast Image Restoration and Enhancement

Given a degraded input image, image restoration aims to recover the missing high-quality image content. Numerous applications demand effective image restoration, e.g., computational photography, surveillance, autonomous vehicles, and remote sensing. Significant advances in image restoration have been made in recent years, dominated by convolutional neural networks (CNNs). The widely-used CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatial details are preserved but the contextual information cannot be precisely encoded. In the latter case, generated outputs are semantically reliable but spatially less accurate. This paper presents a new architecture with a holistic goal of maintaining spatially-precise high-resolution representations through the entire network, and receiving complementary contextual information from the low-resolution representations. The core of our approach is a multi-scale residual block containing the following key elements: (a) parallel multi-resolution convolution streams for extracting multi-scale features, (b) information exchange across the multi-resolution streams, (c) non-local attention mechanism for capturing contextual information, and (d) attention based multi-scale feature aggregation. Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Extensive experiments on six real image benchmark datasets demonstrate that our method, named as MIRNet-v2, achieves state-of-the-art results for a variety of image processing tasks, including defocus deblurring, image denoising, super-resolution, and image enhancement. The source code and pre-trained models are available at https://github.com/swz30/MIRNetv2.

Low light color balancing and denoising by machine learning based approximation for underwater images

It is difficult for underwater archaeologists to recover the fine details of a captured image on the seabed when the image quality worsens due to the presence of more noisy artefacts, a mismatched device colour map, and a blurry image. To resolve this problem, we present a machine learning-based image restoration model (ML-IRM) for improving the visual quality of underwater images that have been deteriorated. Using this model, a home-made bowl set-up is created in which a different liquid concentration is used to replicate seabed water variation, and an object is dipped, or a video is played behind the bowl to recognise the object texture captured image in high-resolution for training the image restoration model is proposed. Gaussian and bidirectional pre-processing filters are used to both the high and low frequency components of the training image, respectively. To improve the clarity of the high-frequency channel background, soft-thresholding decreases the presence of distracting artefacts. On the other hand, the ML-IRM model can effectively keep the object textures on a low frequency channel. Experiment findings show that the proposed ML-IRM model improves the quality of seabed images, eliminates colour mismatches, and allows for more detailed information extraction. Blue shadow, green shadow, hazy, and low light test samples are randomly selected from all five datasets including U45 [1], EUVP [2], DUIE [3], UIEB [4], UM-ImageNet [5], and the proposed model. Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are computed for each condition separately. We list the values of PSNR (at 16.99 dB, 15.96 dB, 18.09 dB, 15.67 dB, 9.39 dB, 17.98 dB, 19.32 dB, 14.27 dB, 12.07 dB, and 25.47 dB) and SSIM (at 0.52, 0.57, 0.33, 0.47, 0.44, and 0.23, respectively. Similarly, it demonstrates that the proposed ML-IRM achieves a satisfactory result in terms of colour correction and contrast adjustment when applied to the problem of improving underwater images captured in low light. To do so, high-resolution images were captured in two low-light conditions (after 6 p.m. and again at 6 a.m.) for the training image datasets, and the results of their observations were compared to those of other existing state-of-the-art-methods.

Mathematical insights into the original Retinex algorithm for image enhancement

The Retinex theory, originally developed by Land and McCann as a computation model of the human color sensation, has become, with time, a pillar of digital image enhancement. In this area, the Retinex algorithm is widely used to improve the quality of any input image by increasing the visibility of its content and details, enhancing its colorfulness, and weakening, or even removing, some undesired effects of the illumination. The algorithm was originally described by its creators in terms of a sequence of image processing operations and was not fully formalized mathematically. Later, works focusing on aspects of the original formulation and adopting some of its principles tried to frame the algorithm within a mathematical formalism: this yielded every time a partial rendering of the model and resulted in several interesting model variants. The purpose of the present work is to fill a gap in the Retinex-related literature by providing a complete mathematical formalization of the original Retinex algorithm. The overarching goals of this work are to provide mathematical insights into the Retinex theory, promote awareness of the use of the model within image enhancement, and enable better appreciation of differences and similarities with later models based on Retinex principles. For this purpose, we compare our model with others proposed in the literature, paying particular attention to the work published in 2005 by Provenzi and others.

Matching visual induction effects on screens of different size

In the film industry, the same movie is expected to be watched on displays of vastly different sizes, from cinema screens to mobile phones. But visual induction, the perceptual phenomenon by which the appearance of a scene region is affected by its surroundings, will be different for the same image shown on two displays of different dimensions. This phenomenon presents a practical challenge for the preservation of the artistic intentions of filmmakers, because it can lead to shifts in image appearance between viewing destinations. In this work, we show that a neural field model based on the efficient representation principle is able to predict induction effects and how, by regularizing its associated energy functional, the model is still able to represent induction but is now invertible. From this finding, we propose a method to preprocess an image in a screen-size dependent way so that its perception, in terms of visual induction, may remain constant across displays of different size. The potential of the method is demonstrated through psychophysical experiments on synthetic images and qualitative examples on natural images.

Vision Models for Wide Color Gamut Imaging in Cinema

Gamut mapping is the problem of transforming the colors of image or video content so as to fully exploit the color palette of the display device where the content will be shown, while preserving the artistic intent of the original content's creator. In particular, in the cinema industry, the rapid advancement in display technologies has created a pressing need to develop automatic and fast gamut mapping algorithms. In this article, we propose a novel framework that is based on vision science models, performs both gamut reduction and gamut extension, is of low computational complexity, produces results that are free from artifacts and outperforms state-of-the-art methods according to psychophysical tests. Our experiments also highlight the limitations of existing objective metrics for the gamut mapping problem.

Different Input Resolutions and Arbitrary Output Resolution: A Meta Learning-Based Deep Framework for Infrared and Visible Image Fusion

Infrared and visible image fusion has gained ever-increasing attention in recent years due to its great significance in a variety of vision-based applications. However, existing fusion methods suffer from some limitations in terms of the spatial resolutions of both input source images and output fused image, which prevents their practical usage to a great extent. In this paper, we propose a meta learning-based deep framework for the fusion of infrared and visible images. Unlike most existing methods, the proposed framework can accept the source images of different resolutions and generate the fused image of arbitrary resolution just with a single learned model. In the proposed framework, the features of each source image are first extracted by a convolutional network and upscaled by a meta-upscale module with an arbitrary appropriate factor according to practical requirements. Then, a dual attention mechanism-based feature fusion module is developed to combine features from different source images. Finally, a residual compensation module, which can be iteratively adopted in the proposed framework, is designed to enhance the capability of our method in detail extraction. In addition, the loss function is formulated in a multi-task learning manner via simultaneous fusion and super-resolution, aiming to improve the effect of feature learning. And, a new contrast loss inspired by a perceptual contrast enhancement approach is proposed to further improve the contrast of the fused image. Extensive experiments on widely-used fusion datasets demonstrate the effectiveness and superiority of the proposed method. The code of the proposed method is publicly available at https://github.com/yuliu316316/MetaLearning-Fusion.

A Cortical-Inspired Sub-Riemannian Model for Poggendorff-Type Visual Illusions

We consider Wilson-Cowan-type models for the mathematical description of orientation-dependent Poggendorff-like illusions. Our modelling improves two previously proposed cortical-inspired approaches, embedding the sub-Riemannian heat kernel into the neuronal interaction term, in agreement with the intrinsically anisotropic functional architecture of V1 based on both local and lateral connections. For the numerical realisation of both models, we consider standard gradient descent algorithms combined with Fourier-based approaches for the efficient computation of the sub-Laplacian evolution. Our numerical results show that the use of the sub-Riemannian kernel allows us to reproduce numerically visual misperceptions and inpainting-type biases in a stronger way in comparison with the previous approaches.

Evidence for the intrinsically nonlinear nature of receptive fields in vision

The responses of visual neurons, as well as visual perception phenomena in general, are highly nonlinear functions of the visual input, while most vision models are grounded on the notion of a linear receptive field (RF). The linear RF has a number of inherent problems: it changes with the input, it presupposes a set of basis functions for the visual system, and it conflicts with recent studies on dendritic computations. Here we propose to model the RF in a nonlinear manner, introducing the intrinsically nonlinear receptive field (INRF). Apart from being more physiologically plausible and embodying the efficient representation principle, the INRF has a key property of wide-ranging implications: for several vision science phenomena where a linear RF must vary with the input in order to predict responses, the INRF can remain constant under different stimuli. We also prove that Artificial Neural Networks with INRF modules instead of linear filters have a remarkably improved performance and better emulate basic human perception. Our results suggest a change of paradigm for vision science as well as for artificial intelligence.

Variational model for simultaneously image denoising and contrast enhancement

The performance of contrast enhancement is degraded when input images are noisy. In this paper, we propose and develop a variational model for simultaneously image denoising and contrast enhancement. The idea is to propose a variational approach containing an energy functional to adjust the pixel values of an input image directly so that the resulting histogram can be redistributed to be uniform and the noise of the image can be removed. In the proposed model, a histogram equalization term is considered for image contrast enhancement, a total variational term is incorporate to remove the noise of the input image, and a fidelity term is added to keep the structure and the texture of the input image. The existence of the minimizer and the convergence of the proposed algorithm are studied and analyzed. Experimental results are presented to show the effectiveness of the proposed model compared with existing methods in terms of several measures: average local contrast, discrete entropy, structural similarity index, measure of enhancement, absolute measure of enhancement, and second derivative like measure of enhancement.

Visual illusions via neural dynamics: Wilson-Cowan-type models and the efficient representation principle

We reproduce suprathreshold perception phenomena, specifically visual illusions, by Wilson-Cowan (WC)-type models of neuronal dynamics. Our findings show that the ability to replicate the illusions considered is related to how well the neural activity equations comply with the efficient representation principle. Our first contribution consists in showing that the WC equations can reproduce a number of brightness and orientation-dependent illusions. Then we formally prove that there cannot be an energy functional that the WC dynamics are minimizing. This leads us to consider an alternative, variational modeling, which has been previously employed for local histogram equalization (LHE) tasks. To adapt our model to the architecture of V1, we perform an extension that has an explicit dependence on local image orientation. Finally, we report several numerical experiments showing that LHE provides a better reproduction of visual illusions than the original WC formulation, and that its cortical extension is capable also to reproduce complex orientation-dependent illusions.NEW & NOTEWORTHY We show that the Wilson-Cowan equations can reproduce a number of brightness and orientation-dependent illusions. Then we formally prove that there cannot be an energy functional that the Wilson-Cowan equations are minimizing, making them suboptimal with respect to the efficient representation principle. We thus propose a slight modification that is consistent with such principle and show that this provides a better reproduction of visual illusions than the original Wilson-Cowan formulation. We also consider the cortical extension of both models to deal with more complex orientation-dependent illusions.

Color gamut mapping between small and large color gamuts: part II. gamut extension

A wide color gamut (WCG) display has great color rendering capability and offers the opportunity to achieve a pleasing and realistic appearance in terms of image quality. To take full advantage of the large display gamut, a new gamut extension algorithm (GEA) is proposed based on a new color appearance scale, vividness. The performance of the new GEA was investigated via a psychophysical experiment together with five commonly used GEAs. In addition, two different uniform color spaces (UCSs) were also studied including the CAM02-UCS color space and a space, J_za_zb_z, designed for high dynamic range (HDR) and WCG applications. The results showed that the newly proposed GEA, i.e. the vividness-extension (VE) algorithm, outperformed all the other GEAs and the J_za_zb_z space was a promising UCS for evaluating gamut extension.

Colour gamut mapping between small and large colour gamuts: Part I. gamut compression

This paper describes an investigation into the performance of different gamut compression algorithms (GCAs) in different uniform colour spaces (UCSs) between small and large colour gamuts. Gamut mapping is a key component in a colour management system and has drawn much attention in the last two decades. Two new GCAs, i.e. vividness-preserved (VP) and depth-preserved (DP), based on the concepts of 'vividness' and 'depth' are proposed and compared with the other commonly used GCAs with the exception of spatial GCAs since the goal of this study was to develop an algorithm that could be implemented in real time for mobile phone applications. In addition, UCSs including CIELAB, CAM02-UCS, and a newly developed UCS, J_za_zb_z, were tested to verify how they affect the performance of the GCAs. A psychophysical experiment was conducted and the results showed that one of the newly proposed GCAs, VP, gave the best performance among different GCAs and the J_za_zb_z is a promising UCS for gamut mapping.

Gamut Extension for Cinema

Emerging display technologies are able to produce images with a much wider color gamut than those of conventional distribution gamuts for cinema and TV, creating an opportunity for the development of gamut extension algorithms (GEAs) that exploit the full color potential of these new systems. In this paper, we present a novel GEA, implemented as a PDE-based optimization procedure related to visual perception models, that performs gamut extension (GE) by taking into account the analysis of distortions in hue, chroma, and saturation. User studies performed using a digital cinema projector under cinematic (low ambient light, large screen) conditions show that the proposed algorithm outperforms the state of the art, producing gamut extended images that are perceptually more faithful to the wide-gamut ground truth, as well as free of color artifacts and hue shifts. We also show how currently available image quality metrics, when applied to the GE problem, provide results that do not correlate with users' choices.

GREAT: a gradient-based color-sampling scheme for Retinex

Modeling the local color spatial distribution is a crucial step for the algorithms of the Milano Retinex family. Here we present GREAT, a novel, noise-free Milano Retinex implementation based on an image-aware spatial color sampling. For each channel of a color input image, GREAT computes a 2D set of edges whose magnitude exceeds a pre-defined threshold. Then GREAT re-scales the channel intensity of each image pixel, called target, by the average of the intensities of the selected edges weighted by a function of their positions, gradient magnitudes, and intensities relative to the target. In this way, GREAT enhances the input image, adjusting its brightness, contrast and dynamic range. The use of the edges as pixels relevant to color filtering is justified by the importance that edges play in human color sensation. The name GREAT comes from the expression "Gradient RElevAnce for ReTinex," which refers to the threshold-based definition of a gradient relevance map for edge selection and thus for image color filtering.

A population-based approach to point-sampling spatial color algorithms

Inspired by the behavior of the human visual system, spatial color algorithms perform image enhancement by correcting the pixel channel lightness based on the spatial distribution of the intensities in the surrounding area. The two visual contrast enhancement algorithms RSR and STRESS belong to this family of models: they rescale the input based on local reference values, which are determined by exploring the image by means of random point samples, called sprays. Due to the use of sampling, they may yield a noisy output. In this paper, we introduce a probabilistic formulation of the two models: our algorithms (RSR-P and STRESS-P) rely implicitly on the whole population of possible sprays. For processing larger images, we also provide two approximated algorithms that exploit a suitable target-dependent space quantization. Those spray population-based formulations outperform RSR and STRESS in terms of the processing time required for the production of noiseless outputs. We argue that this population-based approach, which can be extended to other members of the family, complements the sampling-based approach, in that it offers not only a better control in the design of approximated algorithms, but also additional insight into individual models and their relationships. We illustrate the latter point by providing a model of halo artifact formation.

Energy-driven path search for Termite Retinex

The human color sensation depends on the local and global spatial arrangements of the colors in the scene. Emulating this dependence requires the exploration of the image in search of a white reference. The algorithm Termite Retinex explores the image by a set of paths resembling traces of a swarm of termites. Starting from this approach, we develop a novel spatial exploration scheme where the termite paths are local minimums of an energy function, which depend on the image visual content. The energy is designed to favor the visitation of regions containing information relevant to the color sensation while minimizing the coverage of less essential regions. This exploration method contributes to the investigation of the spatial properties of the color sensation and, to the best of our knowledge, is the first model relying on mathematical global conditions for the Retinex paths. The experiments show that the estimation of the color sensation obtained by means of the proposed spatial sampling is a valid alternative to the one based on Termite Retinex.

A Probabilistic Method for Image Enhancement With Simultaneous Illumination and Reflectance Estimation

In this paper, a new probabilistic method for image enhancement is presented based on a simultaneous estimation of illumination and reflectance in the linear domain. We show that the linear domain model can better represent prior information for better estimation of reflectance and illumination than the logarithmic domain. A maximum a posteriori (MAP) formulation is employed with priors of both illumination and reflectance. To estimate illumination and reflectance effectively, an alternating direction method of multipliers is adopted to solve the MAP problem. The experimental results show the satisfactory performance of the proposed method to obtain reflectance and illumination with visually pleasing enhanced results and a promising convergence rate. Compared with other testing methods, the proposed method yields comparable or better results on both subjective and objective assessments.

Fast Hue and Range Preserving Histogram: Specification: Theory and New Algorithms for Color Image Enhancement

Color image enhancement is a complex and challenging task in digital imaging with abundant applications. Preserving the hue of the input image is crucial in a wide range of situations. We propose simple image enhancement algorithms which conserve the hue and preserve the range (gamut) of the R, G, B channels in an optimal way. In our setup, the intensity input image is transformed into a target intensity image whose histogram matches a specified, well-behaved histogram. We derive a new color assignment methodology where the resulting enhanced image fits the target intensity image. We analyse the obtained algorithms in terms of chromaticity improvement and compare them with the unique and quite popular histogram based hue and range preserving algorithm of Naik and Murthy. Numerical tests confirm our theoretical results and show that our algorithms perform much better than the Naik-Murthy algorithm. In spite of their simplicity, they compete with well-established alternative methods for images where hue-preservation is desired.

From image processing to computational neuroscience: a neural model based on histogram equalization

There are many ways in which the human visual system works to reduce the inherent redundancy of the visual information in natural scenes, coding it in an efficient way. The non-linear response curves of photoreceptors and the spatial organization of the receptive fields of visual neurons both work toward this goal of efficient coding. A related, very important aspect is that of the existence of post-retinal mechanisms for contrast enhancement that compensate for the blurring produced in early stages of the visual process. And alongside mechanisms for coding and wiring efficiency, there is neural activity in the human visual cortex that correlates with the perceptual phenomenon of lightness induction. In this paper we propose a neural model that is derived from an image processing technique for histogram equalization, and that is able to deal with all the aspects just mentioned: this new model is able to predict lightness induction phenomena, and improves the efficiency of the representation by flattening both the histogram and the power spectrum of the image signal.

A no-reference perceptual based contrast enhancement metric for ocean scenes in fog

In this paper, we develop a perceptually based contrast enhancement metric as a means to solve the problem of autonomously enhancing images degraded by fog that are perceptually pleasing to humans. A learning based approach is considered to develop the contrast enhancement using human observations and low-level contrast enhancement metrics based on the human vision system. In addition, we provide new low-level metrics based on the physics of the scene to improve the performance of existing contrast enhancement metrics. This paper shows that a contrast enhancement metric can be designed to mimic human preference.

Variational approach for the fusion of exposure bracketed pairs

When taking pictures of a dark scene with artificial lighting, ambient light is not sufficient for most cameras to obtain both accurate color and detail information. The exposure bracketing feature usually available in many camera models enables the user to obtain a series of pictures taken in rapid succession with different exposure times; the implicit idea is that the user picks the best image from this set. But in many cases, none of these images is good enough; in general, good brightness and color information are retained from longer-exposure settings, whereas sharp details are obtained from shorter ones. In this paper, we propose a variational method for automatically combining an exposure-bracketed pair of images within a single picture that reflects the desired properties of each one. We introduce an energy functional consisting of two terms, one measuring the difference in edge information with the short-exposure image and the other measuring the local color difference with a warped version of the long-exposure image. This method is able to handle camera and subject motion as well as noise, and the results compare favorably with the state of the art.

Image editing with spatiograms transfer

Histogram equalization is a well-known method for image contrast enhancement. Nevertheless, as histograms do not include any information on the spatial repartition of colors, their application to local image editing problems remains limited. To cope with this lack of spatial information, spatiograms have been recently proposed for tracking purposes. A spatiogram is an image descriptor that combines a histogram with the mean and the variance of the position of each color. In this paper, we address the problem of local retouching of images by proposing a variational method for spatiogram transfer. More precisely, a reference spatiogram is used to modify the color value of a given region of interest of the processed image. Experiments on shadow removal and inpainting demonstrate the strength of the proposed approach.

Removing artefacts from color and contrast modifications

This work is concerned with the modification of the gray level or color distribution of digital images. A common drawback of classical methods aiming at such modifications is the revealing of artefacts or the attenuation of details and textures. In this work, we propose a generic filtering method enabling, given the original image and the radiometrically corrected one, to suppress artefacts while preserving details. The approach relies on the key observation that artefacts correspond to spatial irregularity of the so-called transportation map, defined as the difference between the original and the corrected image. The proposed method draws on the nonlocal Yaroslavsky filter to regularize the transportation map. The efficiency of the method is shown on various radiometric modifications: contrast equalization, midway histogram, color enhancement, and color transfer. A comparison with related approaches is also provided.

An Analysis of Visual Adaptation and Contrast Perception for Tone Mapping

Tone Mapping is the problem of compressing the range of a High-Dynamic Range image so that it can be displayed in a Low-Dynamic Range screen, without losing or introducing novel details: The final image should produce in the observer a sensation as close as possible to the perception produced by the real-world scene. We propose a tone mapping operator with two stages. The first stage is a global method that implements visual adaptation, based on experiments on human perception, in particular we point out the importance of cone saturation. The second stage performs local contrast enhancement, based on a variational model inspired by color vision phenomenology. We evaluate this method with a metric validated by psychophysical experiments and, in terms of this metric, our method compares very well with the state of the art.

A PDE formalization of Retinex theory

In 1964 Edwin H. Land formulated the Retinex theory, the first attempt to simulate and explain how the human visual system perceives color. His theory and an extension, the "reset Retinex" were further formalized by Land and McCann. Several Retinex algorithms have been developed ever since. These color constancy algorithms modify the RGB values at each pixel to give an estimate of the color sensation without a priori information on the illumination. Unfortunately, the Retinex Land-McCann original algorithm is both complex and not fully specified. Indeed, this algorithm computes at each pixel an average of a very large set of paths on the image. For this reason, Retinex has received several interpretations and implementations which, among other aims, attempt to tune down its excessive complexity. In this paper, it is proved that if the paths are assumed to be symmetric random walks, the Retinex solutions satisfy a discrete screened Poisson equation. This formalization yields an exact and fast implementation using only two FFTs. Several experiments on color images illustrate the effectiveness of the Retinex original theory.

A perceptually inspired variational framework for color enhancement

Basic phenomenology of human color vision has been widely taken as an inspiration to devise explicit color correction algorithms. The behavior of these models in terms of significative image features (such as, e.g., contrast and dispersion) can be difficult to characterize. To cope with this, we propose to use a variational formulation of color contrast enhancement that is inspired by the basic phenomenology of color perception. In particular, we devise a set of basic requirements to be fulfilled by an energy to be considered as 'perceptually inspired', showing that there is an explicit class of functionals satisfying all of them. We single out three explicit functionals that we consider of basic interest, showing similarities and differences with existing models. The minima of such functionals is computed using a gradient descent approach. We also present a general methodology to reduce the computational cost of the algorithms under analysis from O(N2) to O(N logN), being N the number of pixels of the input image.