Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
This paper proposes a Mamba-based Hybrid Dual-Branch Network (MHDBN) for high-quality multi-focus image fusion (MFIF). The network employs a parallel Mamba-ConvNeXt architecture. The Mamba branch efficiently captures long-range dependencies, while the ConvNeXt branch reinforces local texture representation. These branches are progressively aligned in the Hierarchical Feature Interaction Module (HFIM) and leverage the Multi-Scale Feature Aggregation Module (MSFAM) to adaptively emphasize in-focus regions. Finally, aided by an upsampling module, the model generates precise decision maps and fused outputs. On the three public datasets of Lytro, MFFW and SAVIC, a systematic comparison with 13 of the latest MFIF methods on 12 objective metrics demonstrate that MHDBN achieves the best performance on 6, 10, and 9 metrics, respectively. Notably, on SAVIC MHDBN improves mutual information (MI) by 17.4 % over the second-best method. Extensive quantitative and qualitative results collectively validate the overall superiority of MHDBN.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2025.107916 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
MLP-MFF: Lightweight Pyramid Fusion MLP for Ultra-Efficient End-to-End Multi-Focus Image Fusion.
Sensors (Basel)
August 2025
State Key Laboratory of Ocean Sensing, Ocean College, Zhejiang University, Zhoushan 316021, China.
Limited depth of field in modern optical imaging systems often results in partially focused images. Multi-focus image fusion (MFF) addresses this by synthesizing an all-in-focus image from multiple source images captured at different focal planes. While deep learning-based MFF methods have shown promising results, existing approaches face significant challenges.
View Article and Find Full Text PDFMHDBN: Mamba-based hybrid dual-branch network for multi-focus image fusion.
Neural Netw
August 2025
School of Automation, Central South University, Changsha, 410083, Hunan, China. Electronic address:
This paper proposes a Mamba-based Hybrid Dual-Branch Network (MHDBN) for high-quality multi-focus image fusion (MFIF). The network employs a parallel Mamba-ConvNeXt architecture. The Mamba branch efficiently captures long-range dependencies, while the ConvNeXt branch reinforces local texture representation.
View Article and Find Full Text PDFWavelet-enhanced residual optimal transport for Mamba-based image restoration in photoacoustic tomography.
Photoacoustics
October 2025
Translational and Advanced Bioimaging Laboratory, Department of Chemical and Biological Engineering, The Hong Kong University of Science and Technology, Hong Kong, China.
Photoacoustic tomography (PAT) combines the high contrast of optical imaging with deep tissue penetration via ultrasound detection. However, hardware limitations often cause sparse sampling during image acquisition, resulting in disruptive streak artifacts that many current deep-learning methods fail to remove effectively. In this paper, we introduce Residual Condition Optimal Transport Mamba (RCMamba)-a novel framework that enhances residual optimal transport by integrating wavelet-based analysis with a hybrid multi-scale state space model backbone, specifically designed for sparse PAT image restoration.
View Article and Find Full Text PDFMifnet: a MamBa-based interactive frequency convolutional neural network for motor imagery decoding.
Cogn Neurodyn
December 2025
School of Information Science and Engineering, Yunnan University, Kunming, China.
Motor imagery (MI) decoding remains a critical challenge in brain-computer interface (BCI) systems due to the low signal-to-noise ratio, non-stationarity, and complex spatiotemporal dynamics of electroencephalography (EEG) signals. Although deep learning architectures have advanced MI-EEG decoding, existing approaches-including convolutional neural networks (CNNs), Transformers, and recurrent neural networks (RNNs)-still face limitations in capturing global temporal dependencies, maintaining positional coherence, and ensuring computational efficiency. To address these challenges, we propose MIFNet, a MamBa-based Interactive Frequency Convolutional Neural Network that systematically integrates spectral, spatial, and temporal feature extraction.
View Article and Find Full Text PDFCFM-UNet: coupling local and global feature extraction networks for medical image segmentation.
Sci Rep
July 2025
Beijing Information Science and Technology University, Computer School, Beijing, 100000, China.
In medical image segmentation, traditional CNN-based models excel at extracting local features but have limitations in capturing global features. Conversely, Mamba, a novel network framework, effectively captures long-range feature dependencies and excels in processing linearly arranged image inputs, albeit at the cost of overlooking fine spatial relationships and local pixel interactions. This limitation highlights the need for hybrid approaches that combine the strengths of both architectures.
View Article and Find Full Text PDF