Low-light Imaging Research Articles

Pixel-wise low-light image enhancement based on metropolis theorem

Images taken in low-light conditions frequently encounter visibility problems, such as severe noise, reduced brightness, and low contrast. This paper introduces an approach to enhance low-light images using the Metropolis Theorem (MT). The method begins by applying a global gamma correction to the input image, followed by transforming the globally corrected image into the HSV (Hue, Saturation, Value - V) domain. To achieve multi-scale decomposition, an application of the MT is proposed, resulting in approximation and detail sub-images of the V component. Subsequently, local gamma correction is employed on both the final approximation and detail images to enhance local contrast. The refined approximation and detail images are then combined to reconstruct the refined V component. The reconstructed image is obtained by weighting each band of the image with the refined V component. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods, providing improved visual quality and more natural colors.

Candros optimization algorithm based dual attention LieNet model for low light image enhancement

Candros optimization algorithm based dual attention LieNet model for low light image enhancement

Brightness Perceiving for Recursive Low-Light Image Enhancement

Brightness Perceiving for Recursive Low-Light Image Enhancement

LELD: Learn enhancement by learning degradation

Enhancing low-light images improves both the visibility and quality of the images. Existing methods primarily focus on the enhancement process and heavily rely on the supervised learning strategy, where low/normal-light image pairs are used as the training dataset. In this paper, we propose a novel method called Learn Enhancement by Learning Degradation (LELD) to achieve efficient light adjustment and scene fidelity. We use a carefully designed degradation network (DNet) to guide the enhancement network (ENet). Specifically, the role of DNet is transforming normal-light images into low-light images. For better generalization ability, we employ an unsupervised learning strategy and a generative adversarial network framework. The training is totally dependent on unpaired datasets. Inspired by Retinex theory, we propose a fidelity loss to maintain color and detail during the degradation process. The ENet exhibits a straightforward architecture and achieves efficient enhancement. Experimental results demonstrate the advantages of our method over state-of-the-art methods in terms of visual quality and enhancement efficiency.

A non-uniform low-light image enhancement method with multi-scale attention transformer and luminance consistency loss

A non-uniform low-light image enhancement method with multi-scale attention transformer and luminance consistency loss

Adaptive lightweight Transformer network for low-light image enhancement

Adaptive lightweight Transformer network for low-light image enhancement

Multi-path parallel enhancement of low-light images based on multiscale spatially aware Retinex decomposition

To resolve the issues of color distortion and detail blurring, this study proposes a multi-path parallel enhancement of low-light images (LLIs) based on multiscale spatially aware Retinex decomposition (MUSRetinex-Net). MUSRetinex-Net consists of three subnetworks. Firstly, MUSRetinex-Net inputs LLIs into an illumination level estimation image guided multiscale spatial perception decomposition network (MSPD-Net) which completes Retinex decomposition to retain richer color information and detail structure; then reflectance maps from LLIs are inputted into a three-pass parallel reflectance maps recovery network (TPR-Net) for more desirable noise removal and color recovery; illumination maps from LLIs are inputted into a multi-branch attention illumination maps adjustment network (MAA-Net) for adjustment to obtain a more accurate estimation of illumination levels. In this study, six publicly accessible datasets are utilized for experiments, two referenced evaluation metrics, and four non-referenced evaluation metrics are utilized for assessment and analysis. The experimental results show that the low-light image enhancement (LLIE) effects obtained by this study method are more consistent with the recognition level of the human eye and the structure of the natural environment. The method achieves the optimal referenced evaluation metrics score and the most comprehensive non-referenced evaluation metrics score on all six public datasets, with extremely high enhancement performance and generalization ability.

Reversible data hiding based on global and local automatic contrast enhancement of low-light color images

Currently, many scholars have investigated reversible data hiding (RDH) based on automatic contrast enhancement (ACE). For RDH based on ACE (ACERDH), various methods have been proposed on how to better improve image quality. Preserving brightness can prevent the image from being over-enhanced. However, some ACERDH methods that can preserve brightness well cannot sufficiently enhance low-light images. Although some ACERDH methods that cannot preserve brightness well can more sufficiently enhance low-light color images, they lack the consideration of the local region, which is not conducive to enhancing the contrast of the local region. Therefore, a novel RDH method based on global ACE and local ACE is proposed. The global contrast is first improved by equalizing the global histogram. Then the high complexity region is optimized by the proposed RDH method based on double-layer ACE to further enhance the local contrast. The low-light color image can be well enhanced by applying the proposed method to enhance the R, G, and B channels sequentially. Experimental results demonstrated that the proposed method is superior to some existing advanced methods in obtaining better image quality and hiding more secret data.

A Retinex-based network for image enhancement in low-light environments.

Most of the existing low-light image enhancement methods suffer from the problems of detail loss, color distortion and excessive noise. To address the above-mentioned issues, this paper proposes a neural network-based low-light image enhancement network. The network is divided into three parts: decomposition network, reflection component denoising network, and illumination component enhancement network. In the decomposition network, the input image is decomposed into a reflection image and an illumination image. In the reflection component denoising network, the Unet3+ network improved by fusion CA attention is adopted to denoise the reflection image. In the illumination component enhancement network, the adaptive mapping curve is adopted to enhance the illumination image iteratively. Finally, the processed illumination and reflection images are fused based on Retinex theory to obtain the final enhanced image. The experimental results show that the proposed network achieves excellent visual effects in subjective evaluation. Additionally, it shows a significant improvement in objective evaluation metrics, including PSNR, SSIM, NIQE, and so on, when compared to the results in several public datasets.

Multi-Modular Network-Based Retinex Fusion Approach for Low-Light Image Enhancement

Current low-light image enhancement techniques prioritize increasing image luminance but fail to address issues including loss of intricate distortion of colors and image details. In order to address these issues that has been overlooked by all parties, this paper suggests a multi-module optimization network for enhancing low-light images by integrating deep learning with Retinex theory. First, we create a decomposition network to separate the lighting components and reflections from the low-light image. We incorporated an enhanced global spatial attention (GSA) module into the decomposition network to boost its flexibility and adaptability. This module enhances the extraction of comprehensive information from the image and safeguards against information loss. To increase the illumination component’s luminosity, we subsequently constructed an enhancement network. The Multiscale Guidance Block (MSGB) has been integrated into the improvement network, together with multilayer extended convolution to expand the sensing field and enhance the network’s capability for feature extraction. Our proposed method out-performs existing ways in both objective measures and personal evaluations, emphasizing the virtues of the procedure outlined in this paper.

RRAM based processing-in-memory for efficient intelligent vision tasks at the edge

The work presents a proof-of-concept methodology for at edge visual data storage and processing-in-memory (PIM) as visual data preprocessing inspired from the biological visual system pipeline. This work proposes a methodology to improve the contrast of low-light low-contrast image by carefully modulating the conductance of memristive kind oxide-based resistive memory (RRAM)device. We present the level of contrast enhancement using conductance modulation of different non-filamentary RRAMs with different material stacks and also analyze the impact of RRAM variability on the contrast enhancement. For intelligent vision tasks, we implement artificial neural network (ANN) to perform the image classification and shows the best-case improvement of ∼ 1500 epochs (∼ 74%) using RRAM based PIM. We also implement a large sized ANN “Efficient-Det Network” to perform object recognition on low-light low-contrast dataset ”Ex-Dark” to evaluate the proposed method using PIM layer. The result shows 8% higher mAP than network without a PIM layer. The present work is a step towards the development of efficient hybrid visual system for intelligent vision tasks at edge.

Enhancement of Mine Images through Reflectance Estimation of V Channel Using Retinex Theory

The dim lighting and excessive dust in underground mines often result in uneven illumination, blurriness, and loss of detail in surveillance images, which hinders subsequent intelligent image recognition. To address the limitations of the existing image enhancement algorithms in terms of generalization and accuracy, this paper proposes an unsupervised method for enhancing mine images in the hue–saturation–value (HSV) color space. Inspired by the HSV color space, the method first converts RGB images to the HSV space and integrates Retinex theory into the brightness (V channel). Additionally, a random perturbation technique is designed for the brightness. Within the same scene, a U-Net-based reflectance estimation network is constructed by enforcing consistency between the original reflectance and the perturbed reflectance, incorporating ResNeSt blocks and a multi-scale channel pixel attention module to improve accuracy. Finally, an enhanced image is obtained by recombining the original hue (H channel), brightness, and saturation (S channel), and converting back to the RGB space. Importantly, this image enhancement algorithm does not require any normally illuminated images during training. Extensive experiments demonstrated that the proposed method outperformed most existing unsupervised low-light image enhancement methods, qualitatively and quantitatively, achieving a competitive performance comparable to many supervised methods. Specifically, our method achieved the highest PSNR value of 22.18, indicating significant improvements compared to the other methods, and surpassing the second-best WCDM method by 10.3%. In terms of SSIM, our method also performed exceptionally well, achieving a value of 0.807, surpassing all other methods, and improving upon the second-place WCDM method by 19.5%. These results demonstrate that our proposed method significantly enhanced image quality and similarity, far exceeding the performance of the other algorithms.

A Novel Self-Adaptive Deformable Convolution-Based U-Net for Low-Light Image Denoising

Capturing images under extremely low-light conditions usually suffers from various types of noise due to the limited photon and low signal-to-noise ratio (SNR), which makes low-light denoising a challenging task in the field of imaging technology. Nevertheless, existing methods primarily focus on investigating the precise modeling of real noise distributions while neglecting improvements in the noise modeling capabilities of learning models. To address this situation, a novel self-adaptive deformable-convolution-based U-Net (SD-UNet) model is proposed in this paper. Firstly, deformable convolution is employed to tackle noise patterns with different geometries, thus extracting more reliable noise representations. After that, a self-adaptive learning block is proposed to enable the network to automatically select appropriate learning branches for noise with different scales. Finally, a novel structural loss function is leveraged to evaluate the difference between denoised and clean images. The experimental results on multiple public datasets validate the effectiveness of the proposed method.

Low-Light Sparse Polarization Demosaicing Network (LLSPD-Net): Polarization Image Demosaicing Based on Stokes Vector Completion in Low-Light Environment.

Polarization imaging has achieved a wide range of applications in military and civilian fields such as camouflage detection and autonomous driving. However, when the imaging environment involves a low-light condition, the number of photons is low and the photon transmittance of the conventional Division-of-Focal-Plane (DoFP) structure is small. Therefore, the traditional demosaicing methods are often used to deal with the serious noise and distortion generated by polarization demosaicing in low-light environment. Based on the aforementioned issues, this paper proposes a model called Low-Light Sparse Polarization Demosaicing Network (LLSPD-Net) for simulating a sparse polarization sensor acquisition of polarization images in low-light environments. The model consists of two parts: an intensity image enhancement network and a Stokes vector complementation network. In this work, the intensity image enhancement network is used to enhance low-light images and obtain high-quality RGB images, while the Stokes vector is used to complement the network. We discard the traditional idea of polarization intensity image interpolation and instead design a polarization demosaicing method with Stokes vector complementation. By using the enhanced intensity image as a guide, the completion of the Stokes vector is achieved. In addition, to train our network, we collected a dataset of paired color polarization images that includes both low-light and regular-light conditions. A comparison with state-of-the-art methods on both self-constructed and publicly available datasets reveals that our model outperforms traditional low-light image enhancement demosaicing methods in both qualitative and quantitative experiments.

Modality specific infrared and visible image fusion based on multi-scale rich feature representation under low-light environment

Infrared (IR) and Visible (VIS) image fusion is a critical task in computer vision, which aims to produce high-quality fused images by combining two modal images with complementary information. However, current image fusion techniques neglect the severe degradation of texture and details in low-light environments and do not account for human visual perception. In this paper, a multi-scale image fusion algorithm adapted to the low-light environment is proposed. Firstly, the light distribution of the low-light image is estimated and adjusted based on the gray value probability distribution, resulting in an enhanced VIS image with rich details. Simultaneously, considering the imaging characteristics of the two modal images, a superpixel method is utilized to obtain a saliency map for the IR image, and a multi-scale feature extraction scheme is employed to establish a VIS detail map. Finally, we employ entropy to measure the amount of information in the saliency and detail maps to guide the fusion process. Experimental results from qualitative and quantitative evaluations demonstrate that the fused image conforms to human visual perception, maintains a uniform distribution of pixel intensity, and preserves rich texture features at the edge details.

Low-light image enhancement using transformer with color fusion and channel attention

Low-light image enhancement using transformer with color fusion and channel attention

Learning multi-granularity semantic interactive representation for joint low-light image enhancement and super-resolution

Images captured in challenging conditions often suffer from the co-existence of low contrast and low resolution. However, most joint enhancement methods focus on fitting a direct mapping from degraded images to high-quality images, which proves insufficient to handle complex degradation. To mitigate this, we propose a novel semantic prior guided interactive network (MSIRNet) to enable effective image representation learning for joint low-light enhancement and super-resolution. Specifically, a local HE-based domain transfer strategy is developed to remedy the domain gap between low-light images and the recognition scope of a generic segmentation model, thereby obtaining a rich granularity of semantic prior. To represent hybrid-scale features with semantic attributes, we propose a multi-grained semantic progressive interaction module that formulates an omnidirectional blend self-attention mechanism, facilitating deep interaction between diverse semantic knowledge and visual features. Moreover, employing our feature normalized complementary module that perceives context and cross-feature relationships, MSIRNet adaptively integrates image features with the auxiliary visual atoms provided by the Codebook, endowing the model with high-fidelity reconstruction capability. Extensive experiments demonstrate the superior performance of our MSIRNet, showing its ability to restore visually and perceptually pleasing normal-light high-resolution images.

Detail-preserving noise suppression post-processing for low-light image enhancement

Low-light image enhancement is a challenging task for high-quality image display and visual applications. However, most of the existing methods are difficult to effectively improve brightness and suppress noise. To solve the problem of greatly amplifying noise in many low-light image enhancement methods, this paper presents a detail-preserving noise-suppressing post-processing method for low-light image enhancement. The main idea is that Gamma correction has good performance in noise suppression, by extending the single global parameter of Gamma correction to a Gamma correction map with the same size as the low-light image, we propose an improved domain transform recursive filter to optimize Gamma correction maps, aiming to smooth the Gamma correction map while preserving structural edges, thereby achieving the goal of suppressing noise levels in the enhanced image and preserving the details and contrast of the enhanced image. The proposed post-processing approach addresses the concern of enhancing noise when enhancing low-light images, and the results show that the proposed post-processing method has good detail preservation and noise suppression performance for different advanced low-light image enhancement methods.

A low-light image enhancement model based on anisotropic weighted exponential local derivatives

Low-light images incur several complicated degradations such as low brightness, poor contrast, and higher noise. Retinex theory, which decomposes a low-light image into illumination and reflection components based on local image derivatives, is widely used in the field of shimmering image enhancement. In this paper, we propose a new low-light image enhancement model based on the Retinex theory to reduce the above distortions. To be more specific, we first introduce a new structural texture extractor (NSTE) based on the local image derivatives properties to generate the texture and structure maps of the observed images. Compared to existing structural texture extractors, NSTE has two key designs: anisotropic weighting and adaptive exponential term. The aim is to generate structural maps with clear edge and texture maps with salient details. Subsequently, these two images are used to regularize the illumination and reflection components of the variational decomposition model, respectively. Finally, we developed a luminance correction function and a detail enhancement function to enhance the illumination and reflectance, respectively. This aims to improve the viewing experience, mitigate over-enhancement, and minimize detail distortion. We choose the alternating direction method of multipliers (ADMM) to solve the optimization model. Experimental results on several low-light datasets demonstrate that our proposed method can achieve better quantitative and qualitative performance than state-of-the-art methods.

Conditional generative model with skip-connection structure for low-light image enhancement

Vision-guided coal mine robots often encounter challenges in low-light environments, capturing images marked by poor visibility and significant loss of detail, which complicates the advancement of smart mine safety production. Despite various advancements, achieving high visibility and detailed images through robotic vision sensors remains a formidable task. This paper introduces a conditional generative model incorporating a skip-connection structure to address these issues. We present a novel approach utilizing conditional Generative Adversarial Networks (GNAs) aimed at improving the visibility of image content. This involves an encoder-decoder framework with skip-connections functioning as the generator, and the discriminator, both tailored to enhance image detail. In addition, we implement loss functions integrated with boundary equilibrium constraints to counter the issue of model collapse in conditional GANs, thereby enhancing training stability and image fidelity. Our experimental findings demonstrate that our model delivers competitive results against other state-of-the-art low-light image enhancement models, alongside a standardized training regimen that ensures rapid and consistent convergence.