Learning Color Representations for Low-Light Image Enhancement

Kim, Bomi; Lee, Sunhyeok; Kim, Nahyun; Jang, Donggon; Kim, Dae‐Shik

doi:10.1109/wacv51458.2022.00098

Cited by 16 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…URetinexNet [ 24 ] then established an unfolding Retinex theory to solve the optimization problem in the Retinex theory. Besides the Retinex theory, learning-based networks centered on differentiable histogram equalization [ 25 ], and those guided by wavelet transform [ 26 ] have also been proposed. Deep enhancement networks that integrate traditional low-light theories maintain interpretability while converting the manual parameter optimization process of illumination and detail enhancement into an automated update procedure.…”

Section: Literature Reviewmentioning

confidence: 99%

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Ye,

Wang,

Yang

et al. 2024

Sensors

View full text Add to dashboard Cite

In Advanced Driving Assistance Systems (ADAS), Automated Driving Systems (ADS), and Driver Assistance Systems (DAS), RGB camera sensors are extensively utilized for object detection, semantic segmentation, and object tracking. Despite their popularity due to low costs, RGB cameras exhibit weak robustness in complex environments, particularly underperforming in low-light conditions, which raises a significant concern. To address these challenges, multi-sensor fusion systems or specialized low-light cameras have been proposed, but their high costs render them unsuitable for widespread deployment. On the other hand, improvements in post-processing algorithms offer a more economical and effective solution. However, current research in low-light image enhancement still shows substantial gaps in detail enhancement on nighttime driving datasets and is characterized by high deployment costs, failing to achieve real-time inference and edge deployment. Therefore, this paper leverages the Swin Vision Transformer combined with a gamma transformation integrated U-Net for the decoupled enhancement of initial low-light inputs, proposing a deep learning enhancement network named Vehicle-based Efficient Low-light Image Enhancement (VELIE). VELIE achieves state-of-the-art performance on various driving datasets with a processing time of only 0.19 s, significantly enhancing high-dimensional environmental perception tasks in low-light conditions.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Ye,

Wang,

Yang

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…With the popularity of deep learning, it has been applied in some stitching tasks [14][15][16][17][18][19][20][20][21][22]. Learning-based stitching methods have realized automatic feature learning, end-to-end training and global information synthesis through deep learning networks, improving the robustness and generalization ability of image stitching, especially when dealing with complex scenarios.…”

Section: Introductionmentioning

confidence: 99%

Semantic Aware Stitching for Panorama

Jia,

Li,

Zhang

et al. 2024

Sensors

View full text Add to dashboard Cite

The most critical aspect of panorama generation is maintaining local semantic consistency. Objects may be projected from different depths in the captured image. When warping the image to a unified canvas, pixels at the semantic boundaries of the different views are significantly misaligned. We propose two lightweight strategies to address this challenge efficiently. First, the original image is segmented as superpixels rather than regular grids to preserve the structure of each cell. We propose effective cost functions to generate the warp matrix for each superpixel. The warp matrix varies progressively for smooth projection, which contributes to a more faithful reconstruction of object structures. Second, to deal with artifacts introduced by stitching, we use a seam line method tailored to superpixels. The algorithm takes into account the feature similarity of neighborhood superpixels, including color difference, structure and entropy. We also consider the semantic information to avoid semantic misalignment. The optimal solution constrained by the cost functions is obtained under a graph model. The resulting stitched images exhibit improved naturalness. Extensive testing on common panorama stitching datasets is performed on the algorithm. Experimental results show that the proposed algorithm effectively mitigates artifacts, preserves the completeness of semantics and produces panoramic images with a subjective quality that is superior to that of alternative methods.

show abstract

“…Under low-light circumstances, camera sensors are sensitive and nonlinear to insufficient photons in the light spectrum, causing color distortion even when brightness and noise are corrected. Moreover, Kim et al [8] determined that the histograms of the R, G, and B channels are different and that there is hardly any correlation between them. Consequently, most image enhancement methods in the RGB color space typically cause color distortion because the same mechanism is applied to the R, G, and B channels [9].…”

Section: Introductionmentioning

confidence: 99%

DMT-Net: Deep Multiple Networks for Low-Light Image Enhancement Based on Retinex Model

Duong,

Lee,

Hong

2023

IEEE Access

View full text Add to dashboard Cite

Images captured under low-light conditions are typically prone to undesirable visual phenomena, particularly color distortion and additive noise, that impede the aesthetics and performance of high-level vision tasks. Therefore, developing an enhancement method is necessary to obtain visually pleasing images. This paper proposes deep multiple networks for low-light image enhancement based on the Retinex model (defined as DMT-Net), wherein each network is configured to perform its own role in the YCbCr color space. More specifically, Decoupled-Net is presented to accurately decouple the luminance channel into reflectance and illumination components using the Retinex model. Denoising-Net is connected to Decoupled-Net to eradicate additive noise in the reflectance component. Boosting-Net enhances the illumination component and reduces halo artifacts. In addition, we propose Chrominance-Net to mitigate the distortion of the Cb and Cr channels. Our study also focuses on having a suitable norm order for the loss function based on kurtosis characteristics, such that each network is properly trained to minimize the residual in the training process. Finally, the experimental results prove that our proposed method outperforms numerous other cutting-edge methods in both qualitative and quantitative terms. INDEX TERMSDeep multiple networks, low-light image enhancement, Retinex model, undesirable degradation, YCbCr color space.

show abstract

Learning Color Representations for Low-Light Image Enhancement

Cited by 16 publications

References 21 publications

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles

Semantic Aware Stitching for Panorama

DMT-Net: Deep Multiple Networks for Low-Light Image Enhancement Based on Retinex Model

Contact Info

Product

Resources

About