Learning a Deep Multi-Scale Feature Ensemble and an Edge-Attention Guidance for Image Fusion

• Published in: IEEE transactions on circuits and systems for video technology Vol. 32; no. 1; pp. 105 - 119
• Main Authors: Liu, Jinyuan, Fan, Xin, Jiang, Ji, Liu, Risheng, Luo, Zhongxuan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: attention mechanism; Computer vision; Datasets; deep feature learning; Deep learning; Dictionaries; Feature extraction; Image acquisition; Image edge detection; Image fusion; Image processing; Infrared detectors; Infrared imagery; Inspection; Learning; Modules; Night vision; Task analysis; Training; Trans-Neptunian objects

Image fusion integrates a series of images acquired from different sensors, e.g. , infrared and visible, outputting an image with richer information than either one. Traditional and recent deep-based methods have difficulties in preserving prominent structures and recovering vital textural details f...