Self-supervised Low Light Image Enhancement and Denoising

Zhang, Yu; Di, Xiaoguang; Zhang, Bin; Li, Qingyan; Yan, Shiyu; Wang, Chunhui

doi:10.48550/arxiv.2103.00832

Cited by 5 publications

(6 citation statements)

References 29 publications

(58 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These GAN-based methods were required to select unpaired training data elaborately to achieve satisfactory results. Zhang et al [13,14] proposed a self-supervised Retinex model based on maximum entropy to achieve more convenient image enhancement and added a re-enhancement and denoising network. Zhang et al [15] proposed the Retinex enhancement model with histogram equalization prior (HEP), which provides richer texture and brightness information for image enhancement.…”

Section: Related Work 21 Low-light Image Enhancement Methodsmentioning

confidence: 99%

“…Adding a perceptual loss [40] enhances the detailed information of the output image features, while avoiding the artifacts generated when the fusion prior image is based on pixel fusion. The perceptual loss is defined as follows: (14) where φ l (•) still denote the feature map of the VGG-19 network. l are the layers conv1_2, conv2_2, conv3_3, con4_3, and conv5_3.…”

Section: Three-branch Asymmetric Exposure Fusion Networkmentioning

confidence: 99%

“…The supervised learning-based enhancement methods [10][11][12] need a large number of low/normal light paired images, which limits their ability to generalize to real-world low-light images. In recent years, some self-supervised enhancement methods [13][14][15] based on Retinex theory require only low-light images for training. However, due to the limited range of the illumination map, such methods lack the ability to suppress overexposure in images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion

Huang,

Li,

et al. 2023

Electronics

View full text Add to dashboard Cite

Low-light image enhancement is a challenging task in non-uniform low-light conditions, often resulting in local overexposure, noise amplification, and color distortion. To obtain satisfactory enhancement results, most models must resort to carefully selected paired or multi-exposure data sets. In this paper, we propose a self-supervised framework for non-uniform low-light image enhancement to address these issues, only requiring low-light images on their own for training. We first design a robust Retinex model-based image exposure enhancement network (EENet) to obtain global brightness enhancement and noise removal of images by carefully designing the loss function of each decomposition map. Then, to correct overexposed areas in the enhanced image, we incorporate the inverse image of the low-light image for enhancement using EENet. Furthermore, a three-branch asymmetric exposure fusion network (TAFNet) is designed. The two enhanced images and the original image are used as the TAFNet inputs to obtain a globally well-exposed and detail-rich image. Experimental results demonstrate that our framework outperforms some state-of-the-art methods in visual and quantitative comparisons.

show abstract

Section: Related Work 21 Low-light Image Enhancement Methodsmentioning

confidence: 99%

Section: Three-branch Asymmetric Exposure Fusion Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion

Huang,

Li,

et al. 2023

Electronics

View full text Add to dashboard Cite

show abstract

“…The essence of Zero-DCE is to utilize neural networks to fit the brightness enhancement curves, and then generate the brightness-enhanced image based on the curve and the original image. Zhang et al [32] proposed maximizing the entropy of the channel with the maximum reflection component as a self-supervised enhancement constraint, and introduced the Contrast Enhancement Network (ICE-Net) and the Enhancement Denoising Network (RED-Net) for contrast enhancement and denoising, respectively. Ma et al [33] proposed a self-supervised enhancement framework based on the Retinex illumination estimation principle.…”

Section: Deep Learning-based Image Enhancement Methodsmentioning

confidence: 99%

Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism

Lan

Xue

et al. 2023

Electronics

View full text Add to dashboard Cite

Low-light image enhancement is a crucial preprocessing task in complex vision tasks. It directly impacts object detection, image segmentation, and image recognition outcomes. In recent years, with the continuous development of deep learning techniques, an increasing number of image enhancement methods based on deep learning have emerged. However, due to the high cost of data collection and the limited content of supervised learning datasets, more and more scholars have shifted their focus to the field of unsupervised image enhancement. Unsupervised image enhancement methods do not require paired images of the same scene during the training process, which greatly reduces the threshold for network training. Nevertheless, current unsupervised methods still suffer from issues such as unstable enhancement effects and limited generalization ability. To address these problems, we propose an improved low-light image enhancement method. The proposed method employs the LSGAN as the training architecture and utilizes an attention map network to dynamically generate attention maps that best fit the network enhancement task, which can effectively improve the generalization ability and enhancement performance of the network. Additionally, we adopt an attention mechanism to enhance the subtle details of the image features. Regarding the network training, considering that the traditional convolutional neural network discriminator may not provide effective guidance to the generator in the early stages of training, we propose an improved discriminator structure. The experimental results demonstrate that our method can achieve good enhancement performance on different datasets and has practical value. Although our method has advantages in enhancing low-light images, it also has certain limitations, such as the network size not meeting the requirements for lightweight models and the potential for further improvement under extremely low-light conditions. We will strive to address these issues as comprehensively as possible in our future research.

show abstract

“…The only way is to use relative information in loss function designing, which reduces the assumption of the existence of absolute ground-truth data. Previous unsupervised methods have proposed some useful loss functions, such as normalized gradient loss [40], spatial consistency loss [5,6] and perception loss [34]. However, only some achieve impressive results, mainly due to the ineffective use of more specific constraint information in designing these loss functions.…”

Section: Loss Functionmentioning

confidence: 99%

Unsupervised Low-Light Image Enhancement via Virtual Diffraction Information in Frequency Domain

Zhang¹,

Wang²,

Qin³

et al. 2023

Preprint

View full text Add to dashboard Cite

With the advent of deep learning, significant progress has been made in low-light image enhancement methods. However, deep learning requires enormous paired training data, which is challenging to capture in real-world scenarios.To address this limitation, this paper presents a novel unsupervised low-light image enhancement method, which first introduces the frequency domain features of images in low-light image enhancement tasks. Our work is inspired by imagining a digital image as a spatially varying metaphoric “field of light”, then subjecting the influence of physical processes such as diffraction and coherent detection back onto the original image space via a frequency-domain to spatial-domain transformation (inverse Fourier transform). However, the mathematical model created by this physical process still requires complex manual tuning of the parameters for different scene conditions to achieve the best adjustment. Therefore, we proposed a dual-branch convolution network to estimate pixel-wise and high-order spatial interactions for dynamic range adjustment of the frequency feature of the given low-light image. Guided by the frequency feature from the “field of light” and parameter estimation networks, our method enables dynamic enhancement of low-light images. Extensive experiments have shown that our method performs well compared to state-of-the-art unsupervised, and its performance approximates the level of the state-of-the-art supervised methods qualitatively and quantitatively. At the same time, the light network structure design allows the proposed method to have an extremely fast inference speed(nearly 150 FPS on an NVIDIA 3090 Ti GPU for an image of size 600×400×3 ). Furthermore, the potential benefits of our method to object detection in the dark are discussed.

show abstract

Self-supervised Low Light Image Enhancement and Denoising

Cited by 5 publications

References 29 publications

Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion

Self-Supervised Non-Uniform Low-Light Image Enhancement Combining Image Inversion and Exposure Fusion

Unsupervised Image Enhancement Method Based on Attention Map Network Guidance and Attention Mechanism

Unsupervised Low-Light Image Enhancement via Virtual Diffraction Information in Frequency Domain

Contact Info

Product

Resources

About