AI Paper Atlas

Research map / Architectures and efficiency / CNN design

MobileFusion: Mobile-Friendly Infrared and Visible Image Fusion via Structural Re-parameterization

Yufa Duan, Jialing Huang, Yingying Wang, Weimin Cai, Xinghao Ding, Xiaotong Tu

ICML 2026 · Architectures and efficiency › CNN design · approach: Dense matching and estimation CNNs

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
use RepMBConv instead of standard convolution (ablation)MobileFusion · FMBSSIM: 0.820 -> 0.986Improved
use RepMBConv instead of standard convolution (ablation)MobileFusion · FMBSCD: 1.320 -> 1.601Improved
use RepMBConv instead of standard convolution (ablation)MobileFusion · FMBMI: 2.489 -> 3.299Improved
use RepMBConv instead of conventional re-parameterized design (ablation)MobileFusion · FMBSSIM: 0.916 -> 0.986Improved
use RepMBConv instead of conventional re-parameterized design (ablation)MobileFusion · FMBSCD: 1.431 -> 1.601Improved
use RepMBConv instead of conventional re-parameterized design (ablation)MobileFusion · FMBMI: 2.973 -> 3.299Improved
re-parameterize multi-branch network into single path for inference (ablation)MobileFusion · FMBSSIM: 0.991 -> 0.986No clear effect

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