Research map / Vision-language and multimodal / Cross-modal learning
MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement
Hao Zhang, Yanping Zha, Zizhuo Li, Meiqi Gong, Jiayi Ma
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 |
|---|---|---|---|
| fuse diffusion noise per timestep rather than aggregating branch outputs after diffusion (ablation) | MagicFuse · MFNet | mIoU: 59.74 -> 62.19 | Improved |
| fuse diffusion noise per timestep (ablation) | MagicFuse · MFNet | PSNR: 61.49 -> 63.49 | Improved |
| add cross-spectral knowledge generation branch to IKR-only visible enhancement (ablation) | MagicFuse · MFNet | mIoU: 57.18 -> 62.19 | Improved |
| add segmentation head (ablation) | MagicFuse · MFNet | mIoU: 60.83 -> 62.19 | Improved |
| add segmentation head (ablation) | MagicFuse · MFNet | Qabf: 0.50 -> 0.50 | No clear effect |
| add one-step estimates to fusion weight estimation (ablation) | MagicFuse · MFNet | mIoU: 61.05 -> 62.19 | Improved |
| add one-step estimates to fusion weight (ablation) | MagicFuse · MFNet | EN: 7.28 -> 7.29 | Mixed |
| tune tau to 0.4 (ablation) | MagicFuse · MFNet | image quality and mIoU | Improved |
| apply MagicFuse before SegFormer on Cityscapes | SegFormer · Cityscapes | mIoU: 65.80 -> 66.91 | Improved |
| compare single-image MagicFuse to multi-modal fusion on FMB | MagicFuse · FMB | mIoU: 57.72 -> 55.41 | Hurt |
| use MagicFuse versus degraded visible image | MagicFuse · MFNet | mIoU: 54.09 -> 62.19 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- EMMA — EMMA: Empowering Multi-modal Mamba with Structural and Hierarchical Alignment (ICLR 2025) · better on 3 of 3 shared results
- ControlFusion — ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DreamFuse: Toward Realistic and Seamless Image Fusion Across Diverse Scenarios (TPAMI 2026 · similarity 0.90)
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws (NeurIPS 2025 · similarity 0.89)
- Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach (TPAMI 2025 · similarity 0.89)
- Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond (CVPR 2025 · similarity 0.88)
- Image Fusion via Vision-Language Model (ICML 2024 · similarity 0.87)
- DCEvo: Discriminative Cross-Dimensional Evolutionary Learning for Infrared and Visible Image Fusion (CVPR 2025 · similarity 0.86)
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.
