Ref-MEF: Reference-Guided Flexible Gated Image Reconstruction Network for Multi-Exposure Image Fusion

• Published in: Entropy (Basel, Switzerland) Vol. 26; no. 2; p. 139
• Main Authors: Huang, Yuhui, Zhou, Shangbo, Xu, Yufen, Chen, Yijia, Cao, Kai
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.02.2024
• Subjects: Algorithms; Color imagery; computational photography; Computer vision; convolutional neural networks; Decomposition; Deep learning; Design; Exposure; Image enhancement; image processing; Image quality; Image reconstruction; Machine learning; Methods; Modules; multi-exposure fusion; Neural networks; Principal components analysis; Registration; image processing; computational photography; convolutional neural networks; multi-exposure fusion

Multi-exposure image fusion (MEF) is a computational approach that amalgamates multiple images, each captured at varying exposure levels, into a singular, high-quality image that faithfully encapsulates the visual information from all the contributing images. Deep learning-based MEF methodologies of...