计算机科学
人工智能
编码器
变压器
水准点(测量)
图像融合
深度学习
机器学习
融合
任务(项目管理)
基本事实
图像(数学)
模式识别(心理学)
工程类
电气工程
哲学
操作系统
电压
语言学
系统工程
地理
大地测量学
作者
Linhao Qu,Shaolei Liu,Manning Wang,Zhijian Song
出处
期刊:Cornell University - arXiv
日期:2021-01-01
被引量:12
标识
DOI:10.48550/arxiv.2112.01030
摘要
In this paper, we propose TransMEF, a transformer-based multi-exposure image fusion framework that uses self-supervised multi-task learning. The framework is based on an encoder-decoder network, which can be trained on large natural image datasets and does not require ground truth fusion images. We design three self-supervised reconstruction tasks according to the characteristics of multi-exposure images and conduct these tasks simultaneously using multi-task learning; through this process, the network can learn the characteristics of multi-exposure images and extract more generalized features. In addition, to compensate for the defect in establishing long-range dependencies in CNN-based architectures, we design an encoder that combines a CNN module with a transformer module. This combination enables the network to focus on both local and global information. We evaluated our method and compared it to 11 competitive traditional and deep learning-based methods on the latest released multi-exposure image fusion benchmark dataset, and our method achieved the best performance in both subjective and objective evaluations.
科研通智能强力驱动
Strongly Powered by AbleSci AI