Research map / Architectures and efficiency / CNN design
MobileFusion: Mobile-Friendly Infrared and Visible Image Fusion via Structural Re-parameterization
Yufa Duan, Jialing Huang, Yingying Wang, Weimin Cai, Xinghao Ding, Xiaotong Tu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use RepMBConv instead of standard convolution (ablation) | MobileFusion · FMB | SSIM: 0.820 -> 0.986 | Improved |
| use RepMBConv instead of standard convolution (ablation) | MobileFusion · FMB | SCD: 1.320 -> 1.601 | Improved |
| use RepMBConv instead of standard convolution (ablation) | MobileFusion · FMB | MI: 2.489 -> 3.299 | Improved |
| use RepMBConv instead of conventional re-parameterized design (ablation) | MobileFusion · FMB | SSIM: 0.916 -> 0.986 | Improved |
| use RepMBConv instead of conventional re-parameterized design (ablation) | MobileFusion · FMB | SCD: 1.431 -> 1.601 | Improved |
| use RepMBConv instead of conventional re-parameterized design (ablation) | MobileFusion · FMB | MI: 2.973 -> 3.299 | Improved |
| re-parameterize multi-branch network into single path for inference (ablation) | MobileFusion · FMB | SSIM: 0.991 -> 0.986 | No clear effect |
Closest papers by meaning
- P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation (ECCV 2026 · similarity 0.89)
- MAVFusion: Efficient Infrared and Visible Video Fusion via Motion-Aware Sparse Interaction (ECCV 2026 · similarity 0.87)
- Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption (TPAMI 2024 · similarity 0.87)
- Efficient Rectified Flow for Image Fusion (NeurIPS 2025 · similarity 0.86)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.85)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
