Author(s): Wang, JX (Wang, Jinxin); Xi, XL (Xi, Xiaoli); Li, DM (Li, Dongmei); Li, F (Li, Fang); Zhang, GX (Zhang, Guanxin)

Source: ENTROPY Volume: 25 Issue: 1 Article Number: 169 DOI: 10.3390/e25010169 Published: JAN 2023

Abstract: Multimodal image fusion aims to retain valid information from different modalities, remove redundant information to highlight critical targets, and maintain rich texture details in the fused image. However, current image fusion networks only use simple convolutional layers to extract features, ignoring global dependencies and channel contexts. This paper proposes GRPAFusion, a multimodal image fusion framework based on gradient residual and pyramid attention. The framework uses multiscale gradient residual blocks to extract multiscale structural features and multigranularity detail features from the source image. The depth features from different modalities were adaptively corrected for inter-channel responses using a pyramid split attention module to generate high-quality fused images. Experimental results on public datasets indicated that GRPAFusion outperforms the current fusion methods in subjective and objective evaluations.

Accession Number: WOS:000915585300001

PubMed ID: 36673310

Author Identifiers:

Author        Web of Science ResearcherID        ORCID Number

xi, xiao li                  0000-0002-7242-5695

Wang, Jinxin                  0000-0003-4205-7673

eISSN: 1099-4300

Full Text: https://www.mdpi.com/1099-4300/25/1/169