Scholarlink

<p>Infrared and visible image fusion (vis-ir) enhances diagnostic accuracy in medical imaging and biological analysis. Existing CNN-based and Transformer-based methods face computational inefficiencies in modeling global dependencies. The author proposes VSS-SpatioNet, a lightweight architecture that replaces self-attention in Transformers with a Visual State Space (VSS) module for efficient dependency modeling. The framework employs an asymmetric encoder-decoder with a multi-scale autoencoder and a novel VSS-Spatial (VS) fusion block for local-global feature integration. Evaluations on TNO, Harvard Medical, and RoadScene datasets demonstrate superior performance. On TNO, VSS-SpatioNet achieves state-of-the-art Entropy (En = 7.0058) and Mutual Information (MI = 14.0116), outperforming 12 benchmark methods. For RoadScene, it attains gradient-based fusion performance (<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_93143_Article_IEq1.gif" Format="GIF" Height="18" Rendition="HTML" Resolution="72" Type="Linedraw" Width="23" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:{\text{Q}}_{\text{G}}\)</EquationSource> </InlineEquation>=0.5712), Piella’s metric (<InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_93143_Article_IEq2.gif" Format="GIF" Height="18" Rendition="HTML" Resolution="72" Type="Linedraw" Width="21" /> </InlineMediaObject> <EquationSource Format="TEX">\(\:{\text{Q}}_{\text{S}}\)</EquationSource> </InlineEquation>=0.7926), and average gradient (AG = 5.2994), surpassing prior works. On Harvard Medical, the VS strategy improves Mean Gradient by 18.7% (0.0224 vs. 0.0198) against FusionGAN, validating enhanced feature preservation. Results confirm the framework’s efficacy in medical applications, particularly precise tissue characterization.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

VSS-SpatioNet: a multi-scale feature fusion network for multimodal image integrations

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月18日

查看全文
  • Zeyu Xiang

摘要

Infrared and visible image fusion (vis-ir) enhances diagnostic accuracy in medical imaging and biological analysis. Existing CNN-based and Transformer-based methods face computational inefficiencies in modeling global dependencies. The author proposes VSS-SpatioNet, a lightweight architecture that replaces self-attention in Transformers with a Visual State Space (VSS) module for efficient dependency modeling. The framework employs an asymmetric encoder-decoder with a multi-scale autoencoder and a novel VSS-Spatial (VS) fusion block for local-global feature integration. Evaluations on TNO, Harvard Medical, and RoadScene datasets demonstrate superior performance. On TNO, VSS-SpatioNet achieves state-of-the-art Entropy (En = 7.0058) and Mutual Information (MI = 14.0116), outperforming 12 benchmark methods. For RoadScene, it attains gradient-based fusion performance ( \(\:{\text{Q}}_{\text{G}}\) =0.5712), Piella’s metric ( \(\:{\text{Q}}_{\text{S}}\) =0.7926), and average gradient (AG = 5.2994), surpassing prior works. On Harvard Medical, the VS strategy improves Mean Gradient by 18.7% (0.0224 vs. 0.0198) against FusionGAN, validating enhanced feature preservation. Results confirm the framework’s efficacy in medical applications, particularly precise tissue characterization.