MAGAN: Unsupervised Low-Light Image Enhancement Guided by Mixed-Attention
Most learning-based low-light image enhancement methods typically suffer from two problems. First, they require a large amount of paired data for training, which are difficult to acquire in most cases. Second, in the process of enhancement, image noise is difficult to be removed and may even be ampl...
Saved in:
Main Authors: | Renjun Wang, Bin Jiang, Chao Yang, Qiao Li, Bolin Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
Tsinghua University Press
2022-06-01
|
Series: | Big Data Mining and Analytics |
Subjects: | |
Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2021.9020020 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Uncertainty Estimation in Unsupervised MR-CT Synthesis of Scoliotic Spines
by: Enamundram Naga Karthik, et al.
Published: (2024-01-01) -
QAR Data Imputation Using Generative Adversarial Network with Self-Attention Mechanism
by: Jingqi Zhao, et al.
Published: (2024-03-01) -
Enhancing Low-Light Images with Kolmogorov–Arnold Networks in Transformer Attention
by: Alexandru Brateanu, et al.
Published: (2025-01-01) -
Investigating the effect of loss functions on single-image GAN performance
by: Eyyup YİLDİZ, et al.
Published: (2024-12-01) -
Adversarial Robust Modulation Recognition Guided by Attention Mechanisms
by: Quanhai Zhan, et al.
Published: (2025-01-01)