Results 261 to 270 of about 850,785 (317)

Semantically-guided low-light image enhancement

Pattern Recognition Letters, 2020
Abstract Recently, extensive research efforts have been made on low-light image enhancement. Many novel models have been proposed, such as the ones based on the Retinex theory, multiple exposure fusion, and deep neural networks. However, current models do not directly consider the semantic information in the modeling process.
Junyi Xie, Hao Bian, Yuanhang Wu, Yu Zhao, Linmin Shan, Shijie Hao   +5 more
openaire   +1 more source

Implicit Neural Representation for Cooperative Low-light Image Enhancement

IEEE International Conference on Computer Vision, 2023
The following three factors restrict the application of existing low-light image enhancement methods: unpredictable brightness degradation and noise, inherent gap between metric-favorable and visual-friendly versions, and the limited paired training data.
Shuzhou Yang, M. Ding, Yanmin Wu, Zihan Li, Jian Zhang   +4 more
semanticscholar   +1 more source

DSLR: Deep Stacked Laplacian Restorer for Low-Light Image Enhancement

IEEE transactions on multimedia, 2021
Various images captured in complicated lighting conditions often suffer from deterioration of the image quality. Such poor quality not only dissatisfies the user expectation but also may lead to a significant performance drop in many applications.
Seokjae Lim, Wonjun Kim
semanticscholar   +1 more source

HVI: A New Color Space for Low-light Image Enhancement

Computer Vision and Pattern Recognition
Low-Light Image Enhancement (LLIE) is a crucial computer vision task that aims to restore detailed visual information from corrupted low-light images. Many existing LLIE methods are based on standard RGB (sRGB) space, which often produce color bias and ...
Qingsen Yan, Yixu Feng, Cheng Zhang, Guansong Pang, Kangbiao Shi, Peng Wu, Wei Dong, Jinqiu Sun, Yanning Zhang   +8 more
semanticscholar   +1 more source

Diff-Retinex++: Retinex-Driven Reinforced Diffusion Model for Low-Light Image Enhancement

IEEE Transactions on Pattern Analysis and Machine Intelligence
This paper proposes a Retinex-driven reinforced diffusion model for low-light image enhancement, termed Diff-Retinex++, to address various degradations caused by low light.
Xunpeng Yi, Han Xu, Hao Zhang, Linfeng Tang, Jiayi Ma   +4 more
semanticscholar   +1 more source

LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Models

European Conference on Computer Vision
In this paper, we propose a diffusion-based unsupervised framework that incorporates physically explainable Retinex theory with diffusion models for low-light image enhancement, named LightenDiffusion.
Hai Jiang, Ao Luo, Xiaohong Liu, Songchen Han, Shuaicheng Liu   +4 more
semanticscholar   +1 more source

Extracting Noise and Darkness: Low-Light Image Enhancement via Dual Prior Guidance

IEEE transactions on circuits and systems for video technology (Print)
The complex entanglement between darkness and noise hinders the advance of low-light image enhancement. Most existing methods adopted lightening-then-denoising or embedded a special denoising module into enhancement network without specific noise ...
Huake Wang, Xiaoyang Yan, Xingsong Hou, Kaibing Zhang, Yujie Dun   +4 more
semanticscholar   +1 more source

You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement

arXiv.org
Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. Most existing methods learn the mapping function between low/normal-light images by Deep Neural Networks (DNNs) on sRGB and HSV ...
Yixu Feng, Cheng Zhang, Pei Wang, Peng Wu, Qingsen Yan, Yanning Zhang   +5 more
semanticscholar   +1 more source

Learning With Self-Calibrator for Fast and Robust Low-Light Image Enhancement

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convolutional Neural Networks (CNNs) have shown significant success in the low-light image enhancement task. However, most of existing works encounter challenges in balancing quality and efficiency simultaneously.
Long Ma, Tengyu Ma, Chengpei Xu, Jinyuan Liu, Xin-Yue Fan, Zhongxuan Luo, Risheng Liu   +6 more
semanticscholar   +1 more source

CWNet: Causal Wavelet Network for Low-Light Image Enhancement

IEEE International Conference on Computer Vision
Traditional Low-Light Image Enhancement (LLIE) methods primarily focus on uniform brightness adjustment, often neglecting instance-level semantic information and the inherent characteristics of different features. To address these limitations, we propose
Tongshun Zhang, Ping Liu, Yubing Lu, Mengen Cai, Zijian Zhang, Zhe Zhang, Qiuzhan Zhou   +6 more
semanticscholar   +1 more source