Related references
Note: Only part of the references are listed.
Article
Engineering, Electrical & Electronic
Y. Demir et al.
Summary: Low-light images suffer from poor visibility, severe noise, low contrast, and low brightness. This paper proposes a low-light image enhancement method that applies the HSV transform and a multi-scale decomposition of the SSIF to obtain approximation and detail sub-images of the V component. Contrast-Limited Adaptive Histogram Equalization (CLAHE) is applied to the approximation image for higher contrast, and the amplified detail sub-images are added to reconstruct the enhanced V component. The results show that this method provides better visual quality and more natural colors than state-of-the-art methods.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Computer Science, Theory & Methods
Laith Alzubaidi et al.
Summary: Data scarcity is a major challenge in training deep learning models due to the need for a large amount of labeled data. Manual labeling is costly and time-consuming, and many applications lack sufficient data for training. This paper presents a comprehensive overview of state-of-the-art techniques to address the issue of data scarcity in deep learning and provides recommendations for data acquisition and ensuring the trustworthiness of training datasets.
JOURNAL OF BIG DATA
(2023)
Article
Engineering, Electrical & Electronic
Kai Xu et al.
Summary: This work proposes a structure-texture aware network (STANet) for improving the perceptual quality of low-light images by exploiting the structure and texture features. The image is decomposed into structure and texture components using a fine-scale contour map guided filter, and structure-attention and texture-attention subnetworks are designed to fully exploit the characteristics of these components. A fusion subnetwork with attention mechanisms is utilized to explore the internal correlations among the global and local features.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Long Ma et al.
Summary: The article introduces a new context-sensitive decomposition network architecture (CSDNet) to enhance the quality of low-light images. By constructing two-stream estimation mechanisms and introducing spatially varying illumination guidance, it achieves good results in detail, color, and noise control.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yonghua Zhang et al.
Summary: Images captured under low-light conditions often suffer from poor visibility due to multiple degradation factors. This study proposes a network based on Retinex theory, decomposing images into illumination and reflectance components to enhance image quality. Extensive experiments show the effectiveness and superiority of this method, especially in terms of flexibility and robustness against visual defects.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Computer Science, Artificial Intelligence
Jiaying Liu et al.
Summary: This paper presents a systematic review and evaluation of existing single-image low-light enhancement algorithms, and explores the potential of joint optimization of high-level and low-level vision enhancement through face detection tasks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2021)
Article
Engineering, Electrical & Electronic
Jinjiang Li et al.
Summary: In this study, a neural network called PRIEN was proposed for enhancing low-light images by combining global and local feature extraction methods. The network utilizes a recursive unit for feature extraction and inputs the global feature map in a progressive manner, showing simple yet effective results.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Engineering, Electrical & Electronic
Zhiyuan Zhang et al.
Summary: The paper proposes a cartoon-texture image decomposition model based on low-rank texture prior, which is able to perform perfectly on globally well-patterned images.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Computer Science, Artificial Intelligence
Yifan Jiang et al.
Summary: This paper presents an unsupervised generative adversarial network, called EnlightenGAN, for low-light image enhancement problem, which can be trained without paired data and achieves good generalization and visual quality, outperforming recent methods.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Shijie Hao et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2020)
Article
Computer Science, Artificial Intelligence
Meng Tang et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Jun Xu et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Computer Science, Artificial Intelligence
Xutong Ren et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Engineering, Electrical & Electronic
Laura Florea et al.
DIGITAL SIGNAL PROCESSING
(2019)
Article
Computer Science, Artificial Intelligence
Jianrui Cai et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Mading Li et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Xiaojie Guo et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2017)
Article
Computer Science, Hardware & Architecture
Alex Krizhevsky et al.
COMMUNICATIONS OF THE ACM
(2017)
Article
Computer Science, Artificial Intelligence
Kede Ma et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2015)
Article
Computer Science, Artificial Intelligence
Chulwoo Lee et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2013)
Article
Computer Science, Artificial Intelligence
Debashis Sen et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2011)
