AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction

Xilai Li, Xiaosong Li, Haishu Tan, Tao Ye, Huafeng Li, Hongbin Wang

ECCV 2026 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 0 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
add task-coupled degradation-aware learning strategy (TDAS) (ablation)AMG-Fuse · AWMM-100k SnowQ_M: 0.5097 -> 0.6408Improved
add mask-guided learning strategy (MGLS) (ablation)AMG-Fuse · AWMM-100k RainQ_G: 0.3910 -> 0.4163Improved
add mask-guided cross-modal cross-attention (MCCA) (ablation)AMG-Fuse · AWMM-100k HazeQ_MI: 0.2803 -> 0.3096Improved
use AMG-Fuse instead of AdaIR+fusion pipelinesAMG-Fuse · AWMM-100k Snow/Rain/Hazeseven fusion metrics: Snow Q_M 0.6408 vs 0.5942 (Text-IF)Mixed
apply AMG-Fuse fused images to YOLOv7 detectionAMG-Fuse · M3FD detection (YOLOv7)mAP@0.5: 0.836 -> 0.843Improved
AMG-Fuse vs its pseudo-GT generator EMMA on clean dataAMG-Fuse · MSRS, M3FD, LLVIP (clean)Q_M: MSRS 0.7291 -> 1.5051Improved
AMG-Fuse vs Text-IF on real-world hazeAMG-Fuse · AWMM-100k real-world hazeQ_AB/F: 0.6800 -> 0.5957Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most 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

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