Research map / Vision-language and multimodal / Cross-modal learning
The Source Image is the Best Attention for Infrared and Visible Image Fusion
Song Wang, Xie Han, Liqun Kuang, Boying Wang, Zhongyu Chen, Zherui Qiao, Fan Yang, Xiaoxia Liu, Bingyu Zhang, Zhixun Wang
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 |
|---|---|---|---|
| add V-SCA to I-SCA (ablation) | fusion network · MSRS | VIF: 1.039 -> 1.061 | Improved |
| add V-SCA to I-SCA (ablation) | fusion network · MSRS | MI: 4.571 -> 5.111 | Improved |
| add V-SCA to I-SCA (ablation) | fusion network · MSRS | SCD: 1.721 -> 1.700 | Hurt |
| add V-SCA to I-SCA (ablation) | fusion network · MSRS | SSIM: 0.982 -> 0.981 | No clear effect |
| add I/V-SCA instead of removing them (ablation) | fusion network · MSRS | SSIM: 0.968 -> 0.981 | Improved |
| add I/V-SCA instead of removing them (ablation) | fusion network · MSRS | MI: 5.651 -> 5.111 | Hurt |
| use I/V-SCA instead of Restormer blocks (ablation) | fusion network · MSRS | SCD: 1.681 -> 1.700 | Improved |
| use I/V-SCA instead of Restormer blocks (ablation) | fusion network · MSRS | VIF: 1.063 -> 1.061 | No clear effect |
| use CBSM instead of Conv1x1 (ablation) | fusion network · MSRS | VIF: 1.026 -> 1.061 | Improved |
| use CBSM instead of Conv1x1 (ablation) | fusion network · MSRS | MI: 4.671 -> 5.111 | Improved |
| use CBSM instead of Conv3x3 (ablation) | fusion network · MSRS | SSIM: 0.977 -> 0.981 | Improved |
| use CBSM instead of learnable parameters (ablation) | fusion network · MSRS | MI: 5.303 -> 5.111 | Hurt |
Closest papers by meaning
- Infrared and Visible Image Fusion: From Data Compatibility to Task Adaption (TPAMI 2024 · similarity 0.88)
- Domain Adaptation Guided Infrared and Visible Image Fusion (AAAI 2026 · similarity 0.88)
- Probing Synergistic High-Order Interaction in Infrared and Visible Image Fusion (CVPR 2024 · similarity 0.87)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.86)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.86)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.85)
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.
