Research map / Vision-language and multimodal / Cross-modal learning
MdaIF: Robust One-Stop Multi-Degradation-Aware Image Fusion with Language-Driven Semantics
Jing Li, Yifan Wang, Jiafeng Yan, Renlong Zhang, Bin Yang
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 degraded inputs directly with MdaIF instead of cascading best restoration model with fusion model | MdaIF · MSRS haze | PSNR: 17.260 -> 18.325 (vs DehazeFormer + SAGE) | Improved |
| fuse degraded inputs directly with MdaIF instead of cascaded restoration + fusion | MdaIF · MSRS rain | PSNR: 17.964 -> 18.079 (vs DRSformer + SAGE) | Improved |
| fuse degraded inputs directly with MdaIF instead of cascaded restoration + fusion | MdaIF · MSRS snow | PSNR: 17.267 -> 17.528 (vs HDCWNet + SAGE) | Improved |
| add DCAM channel modulation (with DMoE present) (ablation) | MdaIF · MSRS average | PSNR: 15.350 -> 17.977 | Improved |
| add semantic-prior-guided DMoE (with DCAM present) (ablation) | MdaIF · MSRS average | PSNR: 17.009 -> 17.977 | Improved |
| add DMoE alone without DCAM (ablation) | MdaIF · MSRS average | PSNR: 16.265 -> 15.350 | Hurt |
| add DCAM alone without DMoE (ablation) | MdaIF · MSRS average | PSNR: 16.265 -> 17.009 | Improved |
Closest papers by meaning
- Robust Fusion Controller: Degradation-Aware Image Fusion with Fine-Grained Language Instructions (AAAI 2026 · similarity 0.89)
- ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts (NeurIPS 2025 · similarity 0.88)
- Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion (CVPR 2024 · similarity 0.87)
- Multi-axis Prompt and Multi-dimension Fusion Network for All-in-one Weather-degraded Image Restoration (AAAI 2025 · similarity 0.87)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.86)
- Task-Gated Multi-Expert Collaboration Network for Degraded Multi-Modal Image Fusion (ICML 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.
