Low-light Image Enhancement Method Research Articles

Light-Aware Contrastive Learning for Low-Light Image Enhancement

Low-Light Image Enhancement (LLIE) presents challenges due to texture information loss and uneven illumination, which can distort feature distribution and reduce the quality of the enhanced images. However, current deep learning methods for LLIE only use supervised information from clear images to extract low-light image features, while disregarding the negative information in low-light images (i.e., low illumination and noise). To address these challenges, we propose a novel LLIE method, LACR-VAE, by leveraging the negative information and considering the uneven illumination. In particular, a Light-Aware Contrastive Regularization (LACR) based on contrastive learning is designed to exploit information from both clear and low-light images. The LACR aims to align latent variables of enhanced images with clear images, away from those of low-light images. This allows the method to prioritize essential elements for LLIE and minimize noise and lighting variations. Furthermore, considering the uneven illumination with diverse region sizes and shapes, a Region-CAlibrated Module (RCAM) is present to learn local and global illumination relations among image regions, and an Attention-guided Multi-Scale Module (AMSM) is designed to extract multi-scale features that improve the model’s representation capability. Extensive experiments show that our method achieves superior performance than previous works. Specifically, our method yields a significant enhancement in the NASA testset, achieving an improvement of at least 0.99 in PSNR and 0.0409 in SSIM. Codes and datasets are available at https://github.com/csxuwu/LACR-VAE .

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.

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.

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.

An unsupervised low-light image enhancement method for improving V-SLAM localization in uneven low-light construction sites

Construction robots have been increasingly adopted in construction projects to improve productivity, reduce risk, and speed up work cycles. Visual Simultaneous Localization and Mapping (V-SLAM) technology is widely used in construction robots due to its lightweight weight, cost-effectiveness, and provision of semantic information. On real construction sites, lighting conditions are often challenging due to factors such as uneven lighting intensity, inadequate exposure, or robots in backlit positions (e.g. roughcast houses without artificial lighting, underground car parks), which cause images captured under these conditions to exhibit low signal-to-noise ratio, uneven lighting, color distortion, noise, and other problems. These challenges make the extraction and matching of feature points in V-SLAM difficult, resulting in significant positioning errors or the inability to generate positioning trajectories for construction robotics. Although existing methods for enhancing low-light images can certainly improve image brightness, they still cannot effectively address the localization challenges brought about by low-light construction scenes with uneven illumination and noise. To address the interference of uneven and changing lighting conditions on V-SLAM localization in construction sites, this paper proposes the Unsupervised Reflectance Retinex and Noise model (URRN-Net) to enhance low-light construction images. By using a CNN model based on the Retinex theory to decompose the illumination characteristics of images, we achieve effective brightness restoration of uneven low-light images by utilizing unsupervised loss functions. URRE-Net can reduce the root mean square localization error by >65% compared to low-light images in the ORB-SLAM3 method, and the maximum error is reduced by >71% in on-site experiments. The proposed URRE-Net can be integrated with existing V-SLAM algorithms to provide more robust localization services for low-light construction site applications such as building operations (e.g., interior wall spraying robotic) or construction management tasks (e.g., automatic tunnel inspection).

Swin enhancer: A low-light smart meter image enhancement method with a multi-layered window attention network

Accurate and efficient identification of visual faults in smart meters is significant to the stable operation of the power acquisition system. However, the electricity meter images collected in dim environments have low brightness problems and lack of detail, which will impact subsequent fault identification based on computer vision. From an unsupervised perspective, this paper proposes a low-light smart meter image enhancement method, Swin enhancer. Originating from the Swin Transformer’s window attention mechanism, this paper designs a Multi-layer Swin Transformer Block (MSTB) to extract regional brightness features through the local window’s attention calculation and provide varying degrees of illumination compensation. At the same time, a shift window mechanism is introduced to interact features among the regions and reduce the possibility of overexposure. Extensive experiments on several benchmark and electric meter datasets demonstrate that our method outperforms state-of-the-art methods on multiple image evaluation metrics.

Real-time Attentive Dilated U-Net for Extremely Dark Image Enhancement

Images taken under low-light conditions suffer from poor visibility, color distortion and graininess, all of which degrade the image quality and hamper the performance of downstream vision tasks, such as object detection and instance segmentation in the field of autonomous driving, making low-light enhancement an indispensable basic component of high-level visual tasks. Low-light enhancement aims to mitigate these issues, and has garnered extensive attention and research over several decades. The primary challenge in low-light image enhancement arises from the low signal-to-noise ratio (SNR) caused by insufficient lighting. This challenge becomes even more pronounced in near-zero lux conditions, where noise overwhelms the available image information. Both traditional image signal processing (ISP) pipeline and conventional low-light image enhancement methods struggle in such scenarios. Recently, deep neural networks have been used to address this challenge. These networks take unmodified RAW images as input and produce the enhanced sRGB images, forming a deep learning-based ISP pipeline. However, most of these networks are computationally expensive and thus far from practical use. In this paper, we propose a lightweight model called attentive dilated U-Net (ADU-Net) to tackle this issue. Our model incorporates several innovative designs, including an asymmetric U-shape architecture, dilated residual modules (DRMs) for feature extraction, and attentive fusion modules (AFMs) for feature fusion. The DRMs provide strong representative capability while the AFMs effectively leverage low-level texture information and high-level semantic information within the network. Both modules employ a lightweight design but offer significant performance gains. Extensive experiments demonstrate our method is highly-effective, achieving an excellent balance between image quality and computational complexity, i . e ., taking less than 4ms for a high-definition 4K image on a single GTX 1080Ti GPU and yet maintaining competitive visual quality. Furthermore, our method exhibits pleasing scalability and generalizability, highlighting its potential for widespread applicability.

A Dual-Branch Autoencoder Network for Underwater Low-Light Polarized Image Enhancement

Underwater detection faces uncomfortable illumination conditions, and traditional optical images sensitive to intensity often cannot work well in these conditions. Polarization imaging is a good solution for underwater detection under adverse lighting conditions. However, the process of obtaining polarization information causes it to be more sensitive to noise; serious noise reduces the quality of polarized images and subsequent performance in advanced visual tasks. Unfortunately, the flourishing low-light image enhancement methods applied to intensity images have not demonstrated satisfactory performance when transferred to polarized images. In this paper, we propose a low-light image enhancement paradigm based on the antagonistic properties of polarization parameters. Furthermore, we develop a dual-branch network that relies on a gradient residual dense feature extraction module (GRD) designed for polarized image characteristics and polarization loss, effectively avoiding noise introduced during the direct amplification of brightness, and capable of restoring target contour details. To facilitate a data-driven learning method, we propose a simulation method for underwater low-light polarized images. Extensive experimental results on real-world datasets demonstrate the effectiveness of our proposed approach and its superiority against other state-of-the-art methods.

Rethinking Zero-DCE for Low-Light Image Enhancement

Zero-Reference Deep Curve Estimation (Zero-DCE) is currently one of the most popular low-light image enhancement methods. Through extensive experimentation, we observe that: (i) the excellent performance of Zero-DCE depends on the training data with multiple exposure levels, (ii) it cannot effectively handle uneven light, extremely low light, or overexposed images in natural environments. Therefore, we propose an improved zero-reference dual-illumination deep curve estimation method for low-light image enhancement named Zero-DiDCE, which can enhance, suppress, or maintain light levels for images. The adaptive light enhancement curve was designed to handle images with different exposure levels. An iterator and amplitude controller are designed to control the curve enhancement intensity by calculating the gap between the input image and the optimal light level. Furthermore, instead of the DCE-Net in Zero-DCE only taking the input image as network input, our DiDCE-Net in Zero-DiDCE takes the input image and the inverted input image simultaneously as network input to ensure that the training set contains samples with multiple exposure levels. A piecewise non-reference loss function is designed to guide the training of DiDCE-Net from the perspective of information loss. Qualitative and quantitative experiments show that our method can handle images with different levels of exposure well and outperforms state-of-the-art methods. In addition, the proposed curve and iterator can be integrated into other methods to improve their enhancement effects. The code is available at https://github.com/Wenhui-Luo/Zero-DiDCE.

DCENet-based low-light image enhancement improved by spiking encoding and convLSTM.

The direct utilization of low-light images hinders downstream visual tasks. Traditional low-light image enhancement (LLIE) methods, such as Retinex-based networks, require image pairs. A spiking-coding methodology called intensity-to-latency has been used to gradually acquire the structural characteristics of an image. convLSTM has been used to connect the features. This study introduces a simplified DCENet to achieve unsupervised LLIE as well as the spiking coding mode of a spiking neural network. It also applies the comprehensive coding features of convLSTM to improve the subjective and objective effects of LLIE. In the ablation experiment for the proposed structure, the convLSTM structure was replaced by a convolutional neural network, and the classical CBAM attention was introduced for comparison. Five objective evaluation metrics were compared with nine LLIE methods that currently exhibit strong comprehensive performance, with PSNR, SSIM, MSE, UQI, and VIFP exceeding the second place at 4.4% (0.8%), 3.9% (17.2%), 0% (15%), 0.1% (0.2%), and 4.3% (0.9%) on the LOL and SCIE datasets. Further experiments of the user study in five non-reference datasets were conducted to subjectively evaluate the effects depicted in the images. These experiments verified the remarkable performance of the proposed method.

More Than Lightening: A Self-Supervised Low-Light Image Enhancement Method Capable for Multiple Degradations

More Than Lightening: A Self-Supervised Low-Light Image Enhancement Method Capable for Multiple Degradations

A low-light image enhancement method for personnel safety monitoring in underground coal mines

Intelligent monitoring technology plays an important role in promoting the development of coal mine safety management. Low illumination in the coal mine underground leads to difficult recognition of monitoring images and poor personnel detection accuracy. To alleviate this problem, a low illuminance image enhancement method proposed for personnel safety monitoring in underground coal mines. Specifically, the local enhancement module maps low illumination to normal illumination at pixel level preserving image details as much as possible. The transformer-based global adjustment module is applied to the locally enhanced images to avoid over-enhancement of bright areas and under-illumination of dark areas, and to prevent possible color deviations in the enhancement process. In addition, a feature similarity loss is proposed to constrain the similarity of target features to avoid the possible detrimental effect of enhancement on detection. Experimental results show that the proposed method improves the detection accuracy by 7.1% on the coal mine underground personal dataset, obtaining the highest accuracy compared to several other methods. The proposed method effectively improves the visualization and detection performance of low-light images, which contributes to the personnel safety monitoring in underground coal mines.

A lightness-aware loss for low-light image enhancement

Current low-light image enhancement methods have made great progress on improving the visibility of low-light images. Nevertheless, they pay less attention to preserving visual naturalness and therefore often introduce over-enhancement and local artifacts into their results. To address this issue, it is useful to introduce additional multi-view information of an image into enhancement models, such as illumination distribution. In this context, we propose a simple but effective loss term that expects the originally bright regions in input images and their corresponding enhanced images to be as similar as possible. Via fully exploring the illumination distribution of an image, the loss term makes enhancement models to know which regions should be preserved during training. Therefore, the unnatural effects in output images can be effectively relieved. In our experiments, we incorporate our loss term into several recently proposed low-light image enhancement models. The experimental results on multiple datasets show that over-enhancement and local artifacts can be effectively suppressed by using our loss term.

Improving the perception of low-light enhanced images.

Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric -such as PSNR or SSIM- on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods -that focus on distortion minimization- cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.

Low Light Image Enhancement in License Plate Recognition using URetinex-Net and TRBA

The license plate recognition system currently in use is susceptible to interference from the external environment and performs poorly in low-light conditions. This paper presents a solution for license plate recognition under a low-light environment. We adopted URetinex-Net methods that unfold an optimization issue into a learnable network to decompose a low illumination image into reflectance and illumination layers. We also adopted TRBA, an end-to-end recognition method involving no character segmentation. The experimental results show that the accuracy of the night environment of the proposed method is 80.11% increased by 5.11% compared to without the low light image enhancement method.

Cycle-Retinex: Unpaired Low-Light Image Enhancement via Retinex-Inline CycleGAN

Low-light image enhancement aims to recover normal-light images from the images captured under dim environments. Most existing methods could just improve the light appearance globally whereas failing to handle other degradation such as dense noise, color offset and extremely low-light. Moreover, unsupervised methods proposed in recent years lack reliable physical model as the basis, thus universality is greatly limited. To address these problems, we propose a novel low-light image enhancement method via Retinex-inline cycle-consistent generative adversarial network named Cycle-Retinex, whose training is totally dependent on unpaired datasets. Specifically, we organically combine Retinex theory with CycleGAN, by which we decouple low-light image enhancement task into two sub-tasks, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e.</i> illumination map enhancement and reflectance map restoration. Retinex theory helps CycleGAN simplify low-light image enhancement problem and CycleGAN provides synthetic paired images to guide the training of Retinex decomposition network. We further introduce a self-augmented method to address the color distortion and noise problem, thus making the network learn to enhance low-light images adaptively. Extensive experiments show that the proposed method can achieve promising results. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/mummmml/Cycle-Retinex</uri> .

Lightweight and Fast Low-Light Image Enhancement Method Based on PoolFormer

Lightweight and Fast Low-Light Image Enhancement Method Based on PoolFormer

Low-Light Enhancement Method Based on a Retinex Model for Structure Preservation

Enhancing low-light image visibility is a critical task in computer vision since it helps to improve input for high-level algorithms. High-quality images typically have clear structural information. In previous studies, due to the lack of proper structural guidance, restored images had some problems, such as unclear structural areas and overexposed or underexposed local areas. To address the above problems, in this paper, we introduce a coefficient of variation (COV) with excellent performance in maintaining structural information, and then we propose a low-light image enhancement method that utilizes the COV to extract structural information from images. First, we apply a traditional retinex model to estimate both reflectance and illumination. Second, we use the COV to indicate the degree of dispersion of the input sample, which enables us to obtain a robust structure-distinguishing weight map for low-light images. The weight map is adaptively divided to obtain a structural weight map, which is then used to enhance the gradient image. This process is applied before the reflectance layer of the retinex model. Finally, the result is obtained by using the block coordinate descent method. According to extensive experiments, outstanding results can be achieved by our proposed method in terms of both subjective and objective evaluation metrics in comparison with other state-of-the-art methods. The source code is available at our website <xref ref-type="fn" rid="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">¹</xref> <fn id="fn1" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><label>¹</label> <uri>https://github.com/bbxavi/spcv22</uri> </fn> .

Unsupervised Low-Light Image Enhancement in the Fourier Transform Domain

Low-light image enhancement is an important task in computer vision. Deep learning-based low-light image enhancement has made significant progress. But the current methods also face the challenge of relying on a wide variety of low-light/normal-light paired images and amplifying noise while enhancing brightness. Based on existing experimental observation that most luminance information concentrates on amplitudes while noise is closely related to phases, an unsupervised low-light image enhancement method in the Fourier transform domain is proposed. In our method, the low-light image is firstly transformed into the amplitude component and phase component via Fourier transform. The luminance of low-light image is enhanced by CycleGAN in the amplitude domain, and the phase component is denoising. The cycle consistency losses both in the Fourier transform domain and spatial domain are used in training. The proposed method has been validated on publicly available test sets and shows that our method achieves superior results than other approaches in low-light image enhancement and noise suppression.

Dark2Light: multi-stage progressive learning model for low-light image enhancement.

Due to severe noise and extremely low illuminance, restoring from low-light images to normal-light images remains challenging. Unpredictable noise can tangle the weak signals, making it difficult for models to learn signals from low-light images, while simply restoring the illumination can lead to noise amplification. To address this dilemma, we propose a multi-stage model that can progressively restore normal-light images from low-light images, namely Dark2Light. Within each stage, We divide the low-light image enhancement (LLIE) into two main problems: (1) illumination enhancement and (2) noise removal. Firstly, we convert the image space from sRGB to linear RGB to ensure that illumination enhancement is approximately linear, and design a contextual transformer block to conduct illumination enhancement in a coarse-to-fine manner. Secondly, a U-Net shaped denoising block is adopted for noise removal. Lastly, we design a dual-supervised attention block to facilitate progressive restoration and feature transfer. Extensive experimental results demonstrate that the proposed Dark2Light outperforms the state-of-the-art LLIE methods both quantitatively and qualitatively.