Coarse-to-fine multi-scale attention-guided network for multi-exposure image fusion

Zhao, Huijuan; Zheng, Jian-Qing; Shang, Xiaoke; Zhong, Wei; Liu, Jinyuan

doi:10.1007/s00371-023-02880-4

Cited by 3 publications

(1 citation statement)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IFCNN [11] employed a dualbranch architecture with shared weights, merged features extracted from convolution based on element mean, and proceeded to train the model utilizing perceptual loss and the fundamental loss between the source image sequence and the simulated "ground truth". CFMSAN [26] employs a multi-scale attention-guided network to extract features across various scales, generating attention weight maps of multiple sizes. These weight maps guide the fusion result generation.…”

Section: Existing Mef Methodsmentioning

confidence: 99%

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

Huang,

Zhou,

et al. 2024

Entropy

View full text Add to dashboard Cite

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 often confront obstacles due to the inherent inflexibilities of neural network structures, presenting difficulties in dynamically handling an unpredictable amount of exposure inputs. In response to this challenge, we introduce Ref-MEF, a method for color image multi-exposure fusion guided by a reference image designed to deal with an uncertain amount of inputs. We establish a reference-guided exposure correction (REC) module based on channel attention and spatial attention, which can correct input features and enhance pre-extraction features. The exposure-guided feature fusion (EGFF) module combines original image information and uses Gaussian filter weights for feature fusion while keeping the feature dimensions constant. The image reconstruction is completed through a gated context aggregation network (GCAN) and global residual learning GRL. Our refined loss function incorporates gradient fidelity, producing high dynamic range images that are rich in detail and demonstrate superior visual quality. In evaluation metrics focused on image features, our method exhibits significant superiority and leads in holistic assessments as well. It is worth emphasizing that as the number of input images increases, our algorithm exhibits notable computational efficiency.

show abstract

Section: Existing Mef Methodsmentioning

confidence: 99%