Learning Multi-scale Retinex with Residual Network for Low-Light Image Enhancement

Ma, Long; Lin, Jie; Shang, Jingjie; Zhong, Wei; Fan, Xin; Luo, Zhongxuan; Liu, Risheng

doi:10.1007/978-3-030-60633-6_24

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The theoretical basis of the Retinex model is the three-color theory and color constancy, which removes or reduces the influence of the incident image by the same method to preserve the image of the essential reflective properties of the object as much as possible. Retinex theory has been the subject of ongoing research, leading to the development of algorithms like SSR (single-scale Retinex) [4], MSR (multi-scale Retinex) [5], and MSRCR (multi-scale Retinex with color recovery) [6]. Traditional algorithms have the advantages of a fast processing speed and easy deployment, but they lack references to real lighting conditions and suffer from problems such as noise being retained or amplified, artifacts, and color deviations.…”

Section: Related Workmentioning

confidence: 99%

Low-Light Image Enhancement Method for Electric Power Operation Sites Considering Strong Light Suppression

Xi,

Zhang,

Wang

2023

Applied Sciences

View full text Add to dashboard Cite

Insufficient light, uneven light, backlighting, and other problems lead to poor visibility of the image of an electric power operation site. Most of the current methods directly enhance the low-light image while ignoring local strong light that may appear in the electric power operation site, resulting in overexposure and a poor enhancement effect. Aiming at the above problems, we propose a low-light image enhancement method for electric power operation sites by considering strong light suppression. Firstly, a sliding-window-based strong light judgment method was designed, which used a sliding window to segment the image, and a brightness judgment was performed based on the average value of the deviation and the average deviation of the subimages of the grayscale image from the strong light threshold. Then, a light effect decomposition method based on a layer decomposition network was used to decompose the light effect of RGB images with the presence of strong light and eliminate the light effect layer. Finally, a Zero-DCE (Zero-Reference Deep Curve Estimation) low-light enhancement network based on a kernel selection module was constructed to enhance the low-light images with reduced or no strong light interference. Comparison experiments using the electric power operation private dataset and the SICE (Single Image Contrast Enhancement) Part 2 public dataset showed that our proposed method outperformed the current state-of-the-art low-light enhancement methods in terms of both subjective visual effects and objective evaluation metrics, which effectively improves the image quality of electric power operation sites in low-light environments and provides excellent image bases for other computer vision tasks, such as the estimation of operators’ posture.

show abstract

Section: Related Workmentioning

confidence: 99%

Low-Light Image Enhancement Method for Electric Power Operation Sites Considering Strong Light Suppression

Xi,

Zhang,

Wang

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…and Mitsunaga 2000), multi-exposure image fusion (MEF) has emerged as a primary alternative for HDRI. This approach, propelled by advancements in digital image processing, showcases extensive applicability across diverse domains, such as image enhancement (Liu et al 2020;Jiang et al 2022a;Ma et al 2021bMa et al , 2022aMa et al , 2023 and object detection (Piao et al 2019(Piao et al , 2020Zhang et al 2020c), etc. By merging a series of LDR images with varying exposure levels, it sidesteps hardware constraints, producing images more congruent with human visual perception.…”

Section: Introductionmentioning

confidence: 99%

Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion

Wu,

Fu,

Liu

et al. 2024

AAAI

View full text Add to dashboard Cite

Multi-exposure image fusion (MEF) has emerged as a prominent solution to address the limitations of digital imaging in representing varied exposure levels. Despite its advancements, the field grapples with challenges, notably the reliance on manual designs for network structures and loss functions, and the constraints of utilizing simulated reference images as ground truths. Consequently, current methodologies often suffer from color distortions and exposure artifacts, further complicating the quest for authentic image representation. In addressing these challenges, this paper presents a Hybrid-Supervised Dual-Search approach for MEF, dubbed HSDS-MEF, which introduces a bi-level optimization search scheme for automatic design of both network structures and loss functions. More specifically, we harness a unique dual research mechanism rooted in a novel weighted structure refinement architecture search. Besides, a hybrid supervised contrast constraint seamlessly guides and integrates with searching process, facilitating a more adaptive and comprehensive search for optimal loss functions. We realize the state-of-the-art performance in comparison to various competitive schemes, yielding a 10.61% and 4.38% improvement in Visual Information Fidelity (VIF) for general and no-reference scenarios, respectively, while providing results with high contrast, rich details and colors. The code is available at https://github.com/RollingPlain/HSDS_MEF.

show abstract

“…Existing solutions to this problem have primarily focused on pre-processing techniques such as image enhancement (Mildenhall et al 2022;Liu et al 2023b;Ma et al 2023;Liu et al 2022b), brightness adjustment (Jiang et al 2021), exposure correction (Nguyen et al 2023) and etc. Although these techniques have demonstrated some effectiveness, enhancing dark or overexposure images using 2D enhancement methods does not ensure precise NeRF estimation.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Neural Radiance Fields with Adaptive Multi-Exposure Fusion: A Bilevel Optimization Approach for Novel View Synthesis

Zou,

Li,

Jiang

et al. 2024

AAAI

View full text Add to dashboard Cite

Neural Radiance Fields (NeRF) have made significant strides in the modeling and rendering of 3D scenes. However, due to the complexity of luminance information, existing NeRF methods often struggle to produce satisfactory renderings when dealing with high and low exposure images. To address this issue, we propose an innovative approach capable of effectively modeling and rendering images under multiple exposure conditions. Our method adaptively learns the characteristics of images under different exposure conditions through an unsupervised evaluator-simulator structure for HDR (High Dynamic Range) fusion. This approach enhances NeRF's comprehension and handling of light variations, leading to the generation of images with appropriate brightness. Simultaneously, we present a bilevel optimization method tailored for novel view synthesis, aiming to harmonize the luminance information of input images while preserving their structural and content consistency. This approach facilitates the concurrent optimization of multi-exposure correction and novel view synthesis, in an unsupervised manner. Through comprehensive experiments conducted on the LOM and LOL datasets, our approach surpasses existing methods, markedly enhancing the task of novel view synthesis for multi-exposure environments and attaining state-of-the-art results. The source code can be found at https://github.com/Archer-204/AME-NeRF.

show abstract

Learning Multi-scale Retinex with Residual Network for Low-Light Image Enhancement

Cited by 6 publications

References 12 publications

Low-Light Image Enhancement Method for Electric Power Operation Sites Considering Strong Light Suppression

Low-Light Image Enhancement Method for Electric Power Operation Sites Considering Strong Light Suppression

Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-Free Multi-Exposure Image Fusion

Enhancing Neural Radiance Fields with Adaptive Multi-Exposure Fusion: A Bilevel Optimization Approach for Novel View Synthesis

Contact Info

Product

Resources

About