Low-Light Image Enhancement via Poisson Noise Aware Retinex Model

Kong, Xiangyu; Liu, Lei; Qian, Yunsheng

doi:10.1109/lsp.2021.3096160

Cited by 34 publications

(17 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…is method first selects the filtering kernel according to the image size in the spatial domain and then performs homomorphic filtering in the frequency domain, which can better improve the image contrast; In addition, selecting the filtering function space in HSI space can reduce the amount of computation on the one hand, and improve the color fidelity of the processed image on the other hand [6] e advantages of this algorithm are simple operation and good real-time performance, which can be applied to video processing [10]. Kong et al proposed a nonlinear filtering Retinex algorithm based on subsampling, which down samples the low-resolution part of the image, estimates the illuminance through the nonlinear filtering of the sampled subimage, and then up samples the high-resolution part of the image to obtain the processing results, so as to speed up the operation speed of the algorithm [11,12].…”

Section: Literature Reviewmentioning

confidence: 99%

Application of Multimedia Semantic Extraction Method in Fast Image Enhancement Control

Gao

Chen

et al. 2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

In order to solve the problem that it is difficult to effectively enhance the details of the compressed domain and maintain the overall brightness and clarity of the image when improving the image contrast in the current image enhancement method in the compressed domain, a multimedia semantic extraction method is applied in fast image enhancement control. It has been proposed that thealgorithm that synthesizes training samples according to the Retinex model converts the original low-light image from RGB (red-green-blue) space to HSI (hue saturation intensity) color space, keeps the chrominance and saturation components unchanged, and uses DCNN to enhance the luminance component; finally, it converts the HSI color space to RGB space to get the final enhanced image. The experimental results show that the performance of the model will increase with the increase of the number of convolution kernels, but the increase of the number of convolution kernels will undoubtedly increase the amount of calculation; it can also be found that when the number of network layers is 7, the PSNR of the image output by the model increases. The highest value, increasing the number of network layers, does not necessarily improve the performance of the model; with or without BN, his training method converges more easily than direct RGB image enhancement, with higher average PSNR and SSIM values. The experimental results show that, compared with the traditional Retinex enhancement algorithm and the DCT compression domain enhancement algorithm, the algorithm has better detail enhancement and color preservation effects and can better suppress the block effect.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Application of Multimedia Semantic Extraction Method in Fast Image Enhancement Control

Gao

Chen

et al. 2022

Journal of Control Science and Engineering

View full text Add to dashboard Cite

show abstract

“…Because of the multiplicative nature of the illumination and reflectance relationship, worse estimation accuracy for one of the two will result in worse accuracy for the other. The recent approaches [5][6][7][8]17 solve it by complex solutions. While early studies for low-light enhancement are light-weighted computing, the reflectance component is separated from the illumination and regarded as the enhanced output directly, which often causes over-enhancement 4 .…”

Section: Introductionmentioning

confidence: 99%

“…All filters can be a constant-time property for each filtering radius: min-filtering 21 , Gaussian filtering 22 , and joint bilateral filtering 23 . The recent low-light enhancement approaches [5][6][7][8]17 assume that inverted low-light image looks like haze images, and the inverted image can be enhanced by haze removing approach 24 . With this flow, they use min-filtering and guided image filtering 25,26 as an edge-preserving filter as an analogy to the proposed method.…”

Section: Introductionmentioning

confidence: 99%

“…The theory also indicates that complex scenes caught by HVS are decomposed into relative illumination and reflectance components 2 . There are various multimedia applications based on the relation: low-light enhancement [4][5][6][7][8] , high-dynamic range (HDR) imaging 9 , haze removing 10,11 , under-water image enhancement 12 , shadow removing 13 , denoising 14 , medial imaging 15 , and face recognition 16 .…”

Section: Introductionmentioning

confidence: 99%

“…While early studies for low-light enhancement are light-weighted computing, the reflectance component is separated from the illumination and regarded as the enhanced output directly, which often causes over-enhancement 4 . Current algorithms [5][6][7][8]17 estimate the illumination and reflectance components by adding the prior constraints and obtain the enhanced low-light image by multiplying the reflectance component with the adjusted illumination component.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Retinex-Based Light Source Generation for Relighting up Night Photography

Oishi

Fukushima

2022

Preprint

View full text Add to dashboard Cite

The lighting up of buildings is one of the entertainments that make a city more colorful, and photographer sometimes changes the lighting by using photo-editing applications. This paper proposes a method for automatically performing such an application that follows the Retinex theory. The Retinex theory indicates that the complex scenes caught by the human visual system are decomposed into illumination and reflectance components. Many Retinex-based applications take much cost into the decomposition, while we show that the decomposition accuracy is less dependent on the final output for the nightscape relighting. First, we propose an extracting method of a relighting saliency map using Retinex with edge-preserving filtering. Second, we propose a sampling method to specify the lighting area in the limited area. We show that relighting within the limited area can be represented without illumination and reflectance decomposition. We then show that this fact can be exploited to realize this application using a simple Retinex decomposition of the single-scale Retinex with fast edge-preserving filters to represent various lighting effects. Experimental results show that the proposed sampling method is successful in keeping the illuminated points in bright locations and equally spaced.Also, the proposed various diffusion method can enhance night skyline photographs with various expressions. Our code and dataset are available at https://github.com/norishigefukushima/RelightingUpNightPhotography.

show abstract

A grayscale image enhancement algorithm based on dense residual and attention mechanism

Meng

Yang

et al. 2023

Vis Comput

View full text Add to dashboard Cite

Low-Light Image Enhancement via Poisson Noise Aware Retinex Model

Cited by 34 publications

References 27 publications

Application of Multimedia Semantic Extraction Method in Fast Image Enhancement Control

Application of Multimedia Semantic Extraction Method in Fast Image Enhancement Control

Retinex-Based Light Source Generation for Relighting up Night Photography

A grayscale image enhancement algorithm based on dense residual and attention mechanism

Contact Info

Product

Resources

About