Color Imbalance Research Articles

Dual-Domain Adaptive Synergy GAN for Enhancing Low-Light Underwater Images

The increasing application of underwater robotic systems in deep-sea exploration, inspection, and resource extraction has created a strong demand for reliable visual perception under challenging conditions. However, image quality is severely degraded in low-light underwater environments due to the combined effects of light absorption and scattering, resulting in color imbalance, low contrast, and illumination instability. These factors limit the effectiveness of visual-based autonomous operations. We propose ATS-UGAN, a Dual-domain Adaptive Synergy Generative Adversarial Network for low-light underwater image enhancement to confront the above issues. The network integrates Multi-scale Hybrid Attention (MHA) that synergizes spatial and frequency domain representations to capture key image features adaptively. An Adaptive Parameterized Convolution (AP-Conv) module is introduced to handle non-uniform scattering by dynamically adjusting convolution kernels through a multi-branch design. In addition, a Dynamic Content-aware Markovian Discriminator (DCMD) is employed to perceive the dual-domain information synergistically, enhancing image texture realism and improving color correction. Extensive experiments on benchmark underwater datasets demonstrate that ATS-UGAN surpasses state-of-the-art approaches, achieving 28.7/0.92 PSNR/SSIM on EUVP and 28.2/0.91 on UFO-120. Additional reference and no-reference metrics further confirm the improved visual quality and realism of the enhanced images.

Optimized UNet framework with a joint loss function for underwater image enhancement

As the water economy advances and the concepts of water ecology protection and sustainable development take root in people’s minds, underwater imaging equipment has made remarkable progress. However, due to various factors, underwater images still suffer from low quality. How to enhance the quality of underwater images so that people can understand them quickly has become a crucial issue. Therefore, aiming at the degradation problems such as detail blurring, color imbalance, and noise interference in low-quality underwater images, this paper proposes an optimized UNet framework with a joint loss function (OUNet-JL). Firstly, to alleviate the problem of detail blurring, we construct a multi-residual module (MRM) to enhance the ability to represent detail features by using serially stacked convolutional blocks and residual connections. Secondly, we build a spatial multi-scale feature extraction module fused with channel attention (SMFM) to address the color imbalance issue through multi-scale dilated convolution and channel attention. Thirdly, to improve the signal-to-noise ratio of the enhanced image and solve the problem of blurring distortion, a strengthen-operate-subtract feature reconstruction module (SOSFM) is presented. Fourthly, to guide the network to perform training more efficiently and help it converge rapidly, a joint loss function is designed by integrating four different loss functions. Extensive experiments conducted on the well-known UIEB and UFO-120 datasets have shown the superiority of our OUNet-JL compared with several state-of-the-art algorithms. Moreover, ablation studies have also verified the effectiveness of the proposed modules. Our source code is publicly available at https://github.com/WangXin81/OUNet_JL.

Color Rendering Correctness Estimation of Aerial and Satellite Images and Restoration of Color Balance

Abstract. Despite the fact that with a certain degree of generalization our idea of object’s color around us can be considered the same, the problem of estimation of the color rendering correctness is very relevant for image’s radiometric correction. The color rendering correctness is one of the most important indicators of aerial and space images visual (photographic) quality, since it determines the quality of objects brightness features transmission by the image. In aerial and space imaging for phototopographic surveying (Bianco et al, 2015), to date, neither an indicator of color imbalance nor a method for its estimation has been developed, therefore it is not possible to assess objectively the presence and degree of color imbalance. Amethod for quantitative estimating the color imbalance of an image suggested in paper. The criterion for evaluating the image’s color imbalance, a method for it’s determining and experimental verification of the developed method by correcting the image’s color balance are shown.

A Comprehensive Study of Object Tracking in Low-Light Environments.

Accurate object tracking in low-light environments is crucial, particularly in surveillance, ethology applications, and biometric recognition systems. However, achieving this is significantly challenging due to the poor quality of captured sequences. Factors such as noise, color imbalance, and low contrast contribute to these challenges. This paper presents a comprehensive study examining the impact of these distortions on automatic object trackers. Additionally, we propose a solution to enhance the tracking performance by integrating denoising and low-light enhancement methods into the transformer-based object tracking system. Experimental results show that the proposed tracker, trained with low-light synthetic datasets, outperforms both the vanilla MixFormer and Siam R-CNN.

An underwater image enhancement model for domain adaptation

Underwater imaging has been suffering from color imbalance, low contrast, and low-light environment due to strong spectral attenuation of light in the water. Owing to its complex physical imaging mechanism, enhancing the underwater imaging quality based on the deep learning method has been well-developed recently. However, individual studies use different underwater image datasets, leading to low generalization ability in other water conditions. To solve this domain adaptation problem, this paper proposes an underwater image enhancement scheme that combines individually degraded images and publicly available datasets for domain adaptation. Firstly, an underwater dataset fitting model (UDFM) is proposed to merge the individual localized and publicly available degraded datasets into a combined degraded one. Then an underwater image enhancement model (UIEM) is developed base on the combined degraded and open available clear image pairs dataset. The experiment proves that clear images can be recovered by only collecting the degraded images at some specific sea area. Thus, by use of the scheme in this study, the domain adaptation problem could be solved with the increase of underwater images collected at various sea areas. Also, the generalization ability of the underwater image enhancement model is supposed to become more robust. The code is available at https://github.com/fanren5599/UIEM.

Polynomial color compensation model with neural network solver for color-coded fringe patterns in phase-measuring deflectometry

Polynomial color compensation model with neural network solver for color-coded fringe patterns in phase-measuring deflectometry

Adaptive Phase Error Suppression Concerning 3D surface Deformation Measurement on Color Digital Fringe Projection Profilometry

3D surface measurement based on phase-shifting profilometry (PSP) has been actively developed in recent years. Three color channels of RGB that are modulated to generate a one-shot PSP method is a concept of color digital fringe pattern profilometry (CDFPP). The CDFPP is a promising technique for the 3D imaging profile of dynamic surface deformation if several phase errors in the one-shot PSP method can be suppressed. This work proposes a processing scheme for phase error suppression schemes (PESS) based on retrieving the modulated sinusoidal fringe and color fringe normalization in PSP using RGB color channel. The processing of PESS consists of tunable bandpass filtering (BPF) followed by fringe normalization. The initial BPF function is defined based on a smoothing spline data set of frequency and power spectrum from the baseline color fringe image. The predefine BPF function could be tunable during the imaging process by considering each frame's condition and RGB channel spectrum mapping. The corrected fringe images are then normalized from the color imbalance, and the phase shift is calculated using the conventional three-step PSP. For evaluation, PESS is performed to reconstruct simulator membrane deformation from four different static profiles and tested to observe the 3D surface of continuous membrane deformation. The PESS could suppress the phase errors of less than 30% less absolute errors than the conventional method and successfully reconstruct the 3D surface for low-frequency continuous membrane deformation with minimizing phase errors.

Deep retinex decomposition network for underwater image enhancement

Deep retinex decomposition network for underwater image enhancement

Blind Crosstalk Correction for Color Fringe Projection Profilometry Combining the Sine and Cosine Phase-Shifting Patterns

Color crosstalk is challenging for color fringe projection profilometry, which will cause color imbalance and phase-shift deviation, thus resulting in phase error. To address this challenge, this paper presents a blind crosstalk correction method for color phase-shifting fringe projection profilometry without crosstalk calibration. Three channels of the color fringe are firstly normalized to resolve color imbalance. The phase error induced by phase-shift deviation between three channels doubles the frequency of the color fringe. Therefore, the original cosine color fringe is shifted by quarter period to generate another sine color fringe to compensate the periodic phase error. Both simulations and experiments were carried out, and their results confirmed the effectiveness and accuracy of the proposed method.

Progressive Dual-Branch Network for Low-Light Image Enhancement

Images captured in low light and backlit conditions are characterized by low brightness, low contrast, and varying degrees of degradation. Simply enhancing image contrast will fully expose hidden noise and color distortion, affecting people’s subjective visual perception and performance in other application scenarios. In order to improve the loss of details, color imbalance and artifacts in the enhanced images, we propose a progressive dual branch network(PDBNet) for low-light image enhancement. In this paper, an assisted recovery module(ARM) is designed by exploiting the hybrid correlation and feature complementarity between the inverted image and the low-light image. Feature information at different scales is progressively extracted by cascading multiple ARMs. Considering the network execution efficiency and the amount of parameters, we use depthwise separable convolution(DSC) and asymmetric assisted recovery module(ARM) to improve the computational efficiency of the model. To reduce the degradation caused by enhancing image contrast, the introduction of the large kernel attention(LKA) block allows the network to emphasize hidden low-light information regions, effectively suppressing noise and improving color imbalance. In order to effectively fuse the feature information between the inverse image and the low-light image, an attention fusion block(AFB) is designed. AFB can effectively acquire global feature information and re-encode semantic dependencies between channels. Finally, a fusion reconstruction module(FRM) is designed to further refine the feature information and enhance the information flow between networks. After sufficient qualitative and quantitative experiments in publicly available low-light image datasets, it is known that our method has better visual quality and metric evaluation scores than other state-of-the-art low-light image enhancement methods.

Point-to-point coupling and imbalance correction in color fringe projection profilometry based on multi-confusion matrix

Fringe projection profilometry (FPP) has been widely used in three-dimensional (3D) profile measurements for its efficiency and high accuracy. As an offshoot of FPP, color fringe projection profilometry (CFPP) has the advantage of being dynamic, non-contact, and full-field, which makes it one of the most valuable 3D profile measurement techniques. However, phase errors may arise in CFPP when the phase is retrieved by phase-shifting algorithms. This is due to the gamma nonlinear response, color coupling, and color imbalance of electro-optical devices. In this paper, a multi-confusion matrices (MCM) correction technique is proposed to reduce the phase error by compensating the captured color fringe pattern intensity. This can be accomplished in three steps. Firstly, project 30 ~ 220 (with the step of ten gray levels) uniform intensity patterns on a calibration plate, and then extract the intensity information to construct multi-confusion matrices (MCM) and LUTs (look up tables). Secondly, search optimal confusion matrix (OCM) from MCM to correct the fringe pattern. Finally, retrive the unwrapping phase using the corrected fringe pattern. The simulation and experimental results indicate that the proposed approach can reduce phase errors and use one color fringe pattern to reconstruct 3D topography.

REQUIREMENTS FOR AERIAL IMAGES QUALITY, OBTAINED FOR MAPPING PURPOSES

Abstract. The quality of cartographic products, obtained on base of aerial images, depends on their quality. The image‘s quality can be defined in terms of measurement characteristics and in it’s visual properties. The object of the paper is an aerial image’s quality, concerning its visual perception. The process of topographic aerial images quality assessing is currently not regulated, therefore, this problem becomes particularly relevant today. The article is devoted to development the quality criteria system for aerial images, obtained for mapping purposes, and definition the requirements for them. The analysis of factors affecting the quality of aerial images is carried out, they include natural conditions, technical and technological parameters of aerial surveying and images post-processing. The main imperfections of image quality, appearing as a result of these factors influence are determined – blurring, high level of random image noise, haze, color imbalance, loss of information in shadows and illumination. Methods of identifying these imperfections and assessing their influence on aerial images quality are shown.

Alternative interpretation of color phase-shifting profilometry and a self-contained method for fringe analysis.

This work aims to report a robust single-shot color fringe projection method based on phase-shifting profilometry, where, to calculate the phase, is it not necessary to have knowledge of color coupling or color imbalance calibration parameters of the projector-camera system; additionally, it does not require knowledge of the phase-shifting step, nor projecting equally stepped fringe patterns. Furthermore, it does not require a high density of carrier fringes; it only requires a composite single color image. Theoretical and experimental results are provided. Its suitability to simplify absolute unwrapping is also discussed.

Multiview Ghost-Free Image Enhancement for In-the-Wild Images With Unknown Exposure and Geometry

The multiview low dynamic range images captured with sparse camera arrangement under ill-lighting conditions contain highlighted and shadow regions due to over-exposed and under-exposed regions. The processing of these images produces contrast distortion, and it is challenging to maintain relative brightness with color consistency. Moreover, the disparity map estimation faces the challenges of holes and artifacts due to a wide baseline and poor visibility, with a shared view of vision. In this article, we propose a multiview ghost-free image enhancement strategy for in-the-wild images with unknown exposure and geometry. We address the complex geometric alignment problem for a wide variational baseline among multiple sparsely arranged cameras. The features among multiple viewpoints are detected and matched for the image restoration. The restored image contains highlighted and shadow regions with a color imbalance problem. We synthesize virtual images following the intensity mapping function, which compensates for the relative brightness and color distortions. Finally, we fuse all the images to obtain high-quality images. The proposed method is more frequent and feasible for future multiview systems with varying baselines without relying on disparity maps. The experimental results demonstrate that the proposed method outperformed the state-of-the-art approaches.

Single-shot absolute 3D shape measurement with deep-learning-based color fringe projection profilometry.

Recovering the high-resolution three-dimensional (3D) surface of an object from a single frame image has been the ultimate goal long pursued in fringe projection profilometry (FPP). The color fringe projection method is one of the technologies with the most potential towards such a goal due to its three-channel multiplexing properties. However, the associated color imbalance, crosstalk problems, and compromised coding strategy remain major obstacles to overcome. Inspired by recent successes of deep learning for FPP, we propose a single-shot absolute 3D shape measurement with deep-learning-based color FPP. Through "learning" on extensive data sets, the properly trained neural network can "predict" the high-resolution, motion-artifact-free, crosstalk-free absolute phase directly from one single color fringe image. Compared with the traditional approach, our method allows for more accurate phase retrieval and more robust phase unwrapping. Experimental results demonstrate that the proposed approach can provide high-accuracy single-frame absolute 3D shape measurement for complicated objects.

Human Visual Perception-Based Multi-Exposure Fusion Image Quality Assessment

Compared with ordinary single exposure images, multi-exposure fusion (MEF) images are prone to color imbalance, detail information loss and abnormal exposure in the process of combining multiple images with different exposure levels. In this paper, we proposed a human visual perception-based multi-exposure fusion image quality assessment method by considering the related perceptual features (i.e., color, dense scale invariant feature transform (DSIFT) and exposure) to measure the quality degradation accurately, which is closely related to the symmetry principle in human eyes. Firstly, the L1 norm of chrominance components between fused images and the designed pseudo images with the most severe color attenuation is calculated to measure the global color degradation, and the color saturation similarity is added to eliminate the influence of color over-saturation. Secondly, a set of distorted images under different exposure levels with strong edge information of fused image is constructed through the structural transfer, thus DSIFT similarity and DSIFT saturation are computed to measure the local detail loss and enhancement, respectively. Thirdly, Gauss exposure function is used to detect the over-exposure or under-exposure areas, and the above perceptual features are aggregated with random forest to predict the final quality of fused image. Experimental results on a public MEF subjective assessment database show the superiority of the proposed method with the state-of-the-art image quality assessment models.

Multilayer Fusion and Chunk-Based Transmittance Estimation for Natural Hazy Image Enhancement

Aiming at the uneven distribution of haze concentration and color imbalance in haze weather images, a natural hazy image enhancement method which combines with multilayer fusion and chunk-based is proposed. Based on the atmospheric physical model, the detail and base layers of scene images can be extracted using multilayer decomposition and nonlinear mapping function. Iterative Box Filter can improve the accuracy of ambient light selection and avoid the imbalance of ambient light estimation. The image is segmented into blocks, and the block images are processed by the same operations which are multilayer decomposition and nonlinear mapping function to obtain the detail maps of block images. By splicing these detail maps into the whole detail maps and combining with the dark channel priori, a good transmittance estimation map can be obtained. Throughout the experiment, the guide image filter is utilized to preserve the edges of the image and color correction is added to the model. The experiment results demonstrate that our proposed method can outperform state-of-the-art methods in both qualitative and quantitative comparisons.

Efficient Patch-Wise Semantic Segmentation for Large-Scale Remote Sensing Images

Efficient and accurate semantic segmentation is the key technique for automatic remote sensing image analysis. While there have been many segmentation methods based on traditional hand-craft feature extractors, it is still challenging to process high-resolution and large-scale remote sensing images. In this work, a novel patch-wise semantic segmentation method with a new training strategy based on fully convolutional networks is presented to segment common land resources. First, to handle the high-resolution image, the images are split as local patches and then a patch-wise network is built. Second, training data is preprocessed in several ways to meet the specific characteristics of remote sensing images, i.e., color imbalance, object rotation variations and lens distortion. Third, a multi-scale training strategy is developed to solve the severe scale variation problem. In addition, the impact of conditional random field (CRF) is studied to improve the precision. The proposed method was evaluated on a dataset collected from a capital city in West China with the Gaofen-2 satellite. The dataset contains ten common land resources (Grassland, Road, etc.). The experimental results show that the proposed algorithm achieves 54.96% in terms of mean intersection over union (MIoU) and outperforms other state-of-the-art methods in remote sensing image segmentation.

Метод и алгоритм автоматической оценки качества цветопередачи цифровых аэро- и космических фотоснимков

Today the photographic quality assessment of aerial and space images is made visually, with a big deal of subjectivity. The main problems are the lack of parameters characterizing the photographic quality of images and the lack of methods for determining these parameters. The correctness of color rendition is one of the most important indicators of the photographic aerial and space images’ quality. Research problems included the developing methods for determining the color imbalance of digital images; developing the assessment criterion of color imbalance and a method of its calculation; as well as the experimental verification of the suggested method by correcting the color balance of an image. The article describes the algorithm for automatic color imbalance detection of a digital image that enables searching pixels as parts of gray field areas of an image; the value of a color imbalance is estimated by selected gray pixels. One of the most important indicators of the photographic quality of aerial and space images was determined, it is the color imbalance expressed numerically. The method of automatic assessment of color rendition correctness is offered, the criterion of estimation of color imbalance of the photographic image and a method of its calculation is specified, results of the experimental check of the offered method of assessment of color rendition correctness are given.

Color Transfer Pulse-Coupled Neural Networks for Underwater Robotic Visual Systems

With rapid developments in cloud computing, artificial intelligence, and robotic systems, ever more complex tasks, such as space and ocean exploration, are being implemented by intelligent robots. Here, we propose an underwater image enhancement scheme for robotic visual systems. The proposed algorithm and its implementation enhances and outputs an image captured by an underwater robot in real time. In this scheme, pulse-coupled neural network (PCNN)-based image enhancement and color transfer algorithms are combined to enhance the underwater image. To avoid color imbalance in the underwater image and enhance details while suppressing noise, color correction is first carried out on the underwater image before converting it into the hue–saturation–intensity domain and enhancing it by PCNN. The enhanced result improves the color and contrast of the source image and enhances the details and edges of darker regions. Experiments are performed on real world data to demonstrate the effectiveness of the proposed scheme.