Self-supervised Low-Light Image Enhancement via Histogram Equalization Prior
Deep learning-based methods for low-light image enhancement have achieved remarkable
success. However, the requirement of enormous paired real data limits the generality of …
success. However, the requirement of enormous paired real data limits the generality of …
Extracting Noise and Darkness: Low-Light Image Enhancement via Dual Prior Guidance
H Wang, X Yan, X Hou, K Zhang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The complex entanglement between darkness and noise hinders the advance of low-light
image enhancement. Most existing methods adopted lightening-then-denoising or …
image enhancement. Most existing methods adopted lightening-then-denoising or …
VELIE: A Vehicle-Based Efficient Low-Light Image Enhancement Method for Intelligent Vehicles
L Ye, D Wang, D Yang, Z Ma, Q Zhang - Sensors, 2024 - mdpi.com
In Advanced Driving Assistance Systems (ADAS), Automated Driving Systems (ADS), and
Driver Assistance Systems (DAS), RGB camera sensors are extensively utilized for object …
Driver Assistance Systems (DAS), RGB camera sensors are extensively utilized for object …
Region-Based Unsupervised Low-Light Image Enhancement in the Wild with Explicit Domain Supervision
Prior unsupervised low-light image enhancement methods have exhibited commendable
performance within indoor environments. However, adopting them in the wild scene whose …
performance within indoor environments. However, adopting them in the wild scene whose …
Cyclic Generative Attention-Adversarial Network for Low-Light Image Enhancement
T Zhen, D Peng, Z Li - Sensors, 2023 - mdpi.com
Images captured under complex conditions frequently have low quality, and image
performance obtained under low-light conditions is poor and does not satisfy subsequent …
performance obtained under low-light conditions is poor and does not satisfy subsequent …
RIRO: From Retinex-Inspired Reconstruction Optimization Model to Deep Low-Light Image Enhancement Unfolding Network
L Zhao, B Chen, J Zhang, A Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Low contrast, noise pollution and color distortion of low-light images tremendously affect
human visual perception. The Retinex and its variant models are widely used for low-light …
human visual perception. The Retinex and its variant models are widely used for low-light …
Self-Supervision via Controlled Transformation and Unpaired Self-Conditioning for Low-Light Image Enhancement
Real-world low-light images captured by imaging devices suffer from poor visibility and
require a domain-specific enhancement to produce artifact-free outputs that reveal details …
require a domain-specific enhancement to produce artifact-free outputs that reveal details …
ILSR-Diff: joint face illumination normalization and super-resolution via diffusion models
W Wang, M Mu, Y Tian, Y Hu, X Lu - Multimedia Systems, 2024 - Springer
The existing diffusion models (DMs) have shown impressive performance in face super-
resolution tasks under normal illumination conditions. However, when applied to low …
resolution tasks under normal illumination conditions. However, when applied to low …
低光照图像增强研究方法综述.
彭大鑫， 甄彤， 李智慧 - Journal of Computer Engineering & …, 2023 - search.ebscohost.com
低光照图像增强目的是从低光照条件下恢复细节完整的图像, 并逐渐成为计算机图像处理研究的
热点. 图像成像的质量对于智能安防, 视频监控等场景至关重要, 且在相关行业中有着十分广阔的 …
热点. 图像成像的质量对于智能安防, 视频监控等场景至关重要, 且在相关行业中有着十分广阔的 …
Nighttime Person Re-Identification via Collaborative Enhancement Network with Multi-domain Learning
Prevalent nighttime person re-identification (ReID) methods typically combine image
relighting and ReID networks in a sequential manner. However, their performance …
relighting and ReID networks in a sequential manner. However, their performance …