Contrast Enhancement
Contrast enhancement aims to improve the visibility of features in images and videos by increasing the difference between light and dark regions, crucial for various applications including medical imaging and microscopy. Current research focuses on leveraging deep learning, particularly generative adversarial networks (GANs) and transformers, to achieve contrast enhancement, often incorporating attention mechanisms and multimodal data fusion (e.g., audio-visual) to improve accuracy and efficiency. These advancements are significantly impacting fields like medical diagnosis, where improved image quality can lead to more accurate and timely diagnoses, and also benefit other areas such as underwater imaging and astronomical observation.
Papers
A Time-Intensity Aware Pipeline for Generating Late-Stage Breast DCE-MRI using Generative Adversarial Models
Ruben D. Fonnegra, Maria Liliana Hernández, Juan C. Caicedo, Gloria M. Díaz
TASL-Net: Tri-Attention Selective Learning Network for Intelligent Diagnosis of Bimodal Ultrasound Video
Chengqian Zhao, Zhao Yao, Zhaoyu Hu, Yuanxin Xie, Yafang Zhang, Yuanyuan Wang, Shuo Li, Jianhua Zhou, Jianqiao Zhou, Yin Wang, Jinhua Yu