AI Paper Atlas

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

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 6 citations (OpenAlex)

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 changedWhereMeasuredEffect
fuse degraded inputs directly with MdaIF instead of cascading best restoration model with fusion modelMdaIF · MSRS hazePSNR: 17.260 -> 18.325 (vs DehazeFormer + SAGE)Improved
fuse degraded inputs directly with MdaIF instead of cascaded restoration + fusionMdaIF · MSRS rainPSNR: 17.964 -> 18.079 (vs DRSformer + SAGE)Improved
fuse degraded inputs directly with MdaIF instead of cascaded restoration + fusionMdaIF · MSRS snowPSNR: 17.267 -> 17.528 (vs HDCWNet + SAGE)Improved
add DCAM channel modulation (with DMoE present) (ablation)MdaIF · MSRS averagePSNR: 15.350 -> 17.977Improved
add semantic-prior-guided DMoE (with DCAM present) (ablation)MdaIF · MSRS averagePSNR: 17.009 -> 17.977Improved
add DMoE alone without DCAM (ablation)MdaIF · MSRS averagePSNR: 16.265 -> 15.350Hurt
add DCAM alone without DMoE (ablation)MdaIF · MSRS averagePSNR: 16.265 -> 17.009Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy