AMBCR: Low‐light image enhancement via attention guided multi‐branch construction and Retinex theory

Li, Miao; Zhou, Dongming; Nie, Rencan; Xie, Shidong; Liu, Yanyu

doi:10.1049/ipr2.12173

Cited by 7 publications

(4 citation statements)

References 59 publications

(131 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Liu et al. [14] proposed a brightness‐aware network based on brightness‐aware attention and residue quantized codebook to achieve more natural and realistic enhancement. Combining Retinex theory with deep learning achieved unexpected results.…”

Section: Related Workmentioning

confidence: 99%

UM‐GAN: Underground mine GAN for underground mine low‐light image enhancement

Han,

Xiao,

Yin

2024

IET Image Processing

View full text Add to dashboard Cite

In recent years, low‐light image enhancement has become increasingly active. However, in underground mine environments, acquiring high‐quality images is still challenging due to low light, low contrast, and occlusion. To address this problem, this study proposes a low‐light image enhancement method for underground mine based on generative adversarial networks (UM‐GAN), which aims to take full advantage of the ability of GAN to achieve the restoration of details, the reduction of noise, and the improvement of overall image quality. The model proposed in this paper is divided into three main parts. Initially, a generator network adopting an encoder–decoder structure is developed. Subsequently, a novel strategy is introduced to merge information by utilizing inverted greyscale images and low‐light images as inputs. Further image quality enhancement is achieved by incorporating a noise reduction module employing the diffusion model. To ascertain the efficacy of the UM‐GAN method, evaluations are conducted on diverse real‐world and synthetic datasets, juxtaposing the approach against superior methods. Through qualitative and quantitative comparative experiments, the method showcases noteworthy advancements through qualitative and quantitative comparative experiments, substantiating its effectiveness. This research provides new ideas and methods for overcoming image quality problems in underground mine environments and contributes to the development of underground mine image processing.

show abstract

Section: Related Workmentioning

confidence: 99%

UM‐GAN: Underground mine GAN for underground mine low‐light image enhancement

Han,

Xiao,

Yin

2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Then, the preliminary denoised image is enhanced using adaptive gamma transform [8]. Assuming the denoised image format is uint9, the expression for gamma transform is equation (1). In equation ( 1), I in means the brightness of the denoised image.…”

Section: Multi Frame Image Enhancement and Brightness Equalization Al...mentioning

confidence: 99%

Image Enhancement and Brightness Equalization Algorithms in Low Illumination Environment Based on Multiple Frame Sequences

Yan

2023

IEEE Access

View full text Add to dashboard Cite

Images captured in low illumination environments can affect people's judgment of image information. To raise the visual effect of low illumination images and preserve the integrity of image information, this study proposes two algorithms. One is an image enhancement algorithm for low illumination, which combines the WASOBI image denoising method for deep denoising of images and adaptive gamma correction for brightness adjustment of images. The other is an image brightness equalization algorithm for uneven lighting. This algorithm divides the image according to the illumination area, and uses guided filtering and adaptive gamma correction to equalize the brightness of the image. The laboratory outcomes demonstrate that the proposed image enhancement algorithm can effectively reduce the noise level of the image and adjust the brightness of the image, and the algorithm has a certain degree of stability. The subjective evaluation score of the image processed using the brightness equalization algorithm is 4.7, indicating that the image has good visual effects. The objective evaluation results prove the capability of the equilibrium algorithm, and comparing to other algorithms, the algorithm has the shortest operation time, only 0.9452 seconds. Therefore, the enhancement algorithm and brightness equalization algorithm proposed in the article have certain application value.

show abstract

“…Jiang et al [20] propose an attention guided U-net to generate enhanced image, but it is also based on retinex theory. The retinex theory still plays a vital role in recent researches [44,45].…”

Section: Image Quality Enhancementmentioning

confidence: 99%

Image quality enhancement using hybrid attention networks

Wang

Chen

Yan

2021

IET Image Processing

View full text Add to dashboard Cite

Image quality enhancement aims to recover rich details from degraded images, which is applied into many fields, such as medical imaging, filming production and autonomous driving. Deep convolutional neural networks (CNNs) have enabled rapid development of image quality enhancement. However, most existing CNN-based methods lack versatility when targeting different subtasks in terms of the design of networks. Besides, they often fail to balance precise spatial representations and necessary contextual information. To deal with these problems, this paper proposes a novel unified framework for low-light image enhancement, image denoising and image super-resolution. The core of this architecture is a residual hybrid attention block (RHAB), which consists of several dynamic down-sampling modules (DDM) and hybrid attention up-sampling modules (HAUM). Specifically, multi-scale feature maps are fully interacted with each other with the help of nested subnetworks so that both high-resolution spatial details and high-level contextual information can be combined to improve the representation ability of the network. Further, a hybrid attention network (HAN) is proposed and evaluations on three separate subtasks demonstrate its good performance. Extensive experiments on the authors' synthetic dataset, a more complex version, show that the authors' method achieve better quantitative and visual results compared to other state-of-the-art methods.

show abstract

AMBCR: Low‐light image enhancement via attention guided multi‐branch construction and Retinex theory

Cited by 7 publications

References 59 publications

UM‐GAN: Underground mine GAN for underground mine low‐light image enhancement

UM‐GAN: Underground mine GAN for underground mine low‐light image enhancement

Image Enhancement and Brightness Equalization Algorithms in Low Illumination Environment Based on Multiple Frame Sequences

Image quality enhancement using hybrid attention networks

Contact Info

Product

Resources

About