AI Paper Atlas

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

LGD-Net: Leader-Guided Cross-Modal Dynamics for Hyperspectral and Panchromatic Image Fusion

Raj kumar, Balasubramanian Raman, Pravendra Singh

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 continuous cross-modal dynamics on the leader (vs residual stacking) (ablation)LGD-Net · ablation datasetPSNR: 32.725 -> 44.896Improved
add leader-guided refinement (ablation)LGD-Net · ablation datasetPSNR: 43.818 -> 44.896Improved
add graph propagation (ablation)LGD-Net · ablation datasetPSNR: 43.972 -> 44.896Improved
use bilinear (multiplicative) interaction instead of linear (ablation)LGD-Net · ablation datasetPSNR: 44.201 -> 44.896Improved
add edge gating (ablation)LGD-Net · ablation datasetPSNR: 44.385 -> 44.896Improved
use T=2 RK2 steps instead of 1 (ablation)LGD-Net · BotswanaPSNR: 36.142 -> 41.856Improved
increase RK2 steps from 2 to 4 (ablation)LGD-Net · BotswanaPSNR: 41.856 -> 40.562Hurt
increase step scale from 1.2 to 1.8 (ablation)LGD-Net · BotswanaPSNR: 41.856 -> 39.803Hurt
LGD-Net vs best baseline on SAMLGD-Net · ChikuseiSAM: 3.635 -> 3.996Hurt

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