GALFusion: Multi-Exposure Image Fusion via a Global–Local Aggregation Learning Network

Jia Lei, Jiawei Li, Jinyuan Liu, Shihua Zhou, Qiang Zhang, Nikola Kasabov

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)
189 Downloads (Pure)


The goal of multi-exposure image fusion is to generate synthetic results with abundant details and balanced exposure from low dynamic range (LDR) images. The existing multi-exposure fusion (MEF) methods often use convolution operations to extract features. However, these methods only consider the pixel values in local view field and ignore the long-range dependencies between pixels. To solve the aforementioned problem, we propose a global-local aggregation network for fusing extreme exposure images in an unsupervised way. Firsty, we design a collaborative aggregation module (CAM), composed of two submodules covering a nonlocal attention inference (NLAI) module and a local adaptive learning module, to mine the relevant features from source images. So that we successfully formulate a feature extraction mechanism with aggregating global and local information. Secondly, we provide a special fusion module (FM) to reconstruct fused images, which effectively avoids artifacts and suppresses information decay. Moreover, we further fine-tune the fusion results by a recursive refinement module (RRM) to capture more textural details from source images. The results of both comparative and ablation analyses on two datasets demonstrate that GALFusion achieves the best marks in terms of MEF-structure similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR), outperforming the existing 12 state-of-the-art fusion methods.

Original languageEnglish
Article number5011915
Pages (from-to)16
Number of pages16
JournalIEEE Transactions on Instrumentation and Measurement
Publication statusPublished (in print/issue) - 21 Apr 2023

Bibliographical note

Publisher Copyright:
© 1963-2012 IEEE.


  • Feature extraction
  • Image color analysis
  • Transforms
  • Task analysis
  • Image fusion
  • Convolutional neural networks
  • Collaboration
  • recursive refinement network
  • image fusion
  • multi-exposure image
  • nonlocal attention (NLA)
  • Collaborative extraction


Dive into the research topics of 'GALFusion: Multi-Exposure Image Fusion via a Global–Local Aggregation Learning Network'. Together they form a unique fingerprint.

Cite this