AI Paper Atlas

Research map / Image generation / Image restoration

UHD-MFF: Shattering Barriers in Multi-Focus Ultra-High-Definition Image Fusion via Learnable Lookup Tables

Yibing Zhang, Xunpeng Yi, Qinglong Yan, Yeda Wang, Han Xu, Jiayi Ma

ECCV 2026 · Image generation › Image restoration · approach: Pansharpening and spectral 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 dilated gradient cue to the C-LUT (ablation)UMF-LUT · UHD-MFF-SynVIF: 1.2564 -> 1.4335Improved
add gradient difference cue to the C-LUT (ablation)UMF-LUT · UHD-MFF-SynVIF: 1.4028 -> 1.4335Improved
add maximum gradient cue to the C-LUT (ablation)UMF-LUT · UHD-MFF-SynVIF: 1.3948 -> 1.4335Improved
add learnable regional semantic cue to the C-LUT (ablation)UMF-LUT · UHD-MFF-Synspatial frequency: 5.8832 -> 6.7443Improved
add the Detail-Edge LUT branch (ablation)UMF-LUT · UHD-MFF-Synaverage gradient: 1.8479 -> 1.9416Improved
train on 1500 pairs instead of 15 (ablation)UMF-LUT · UHD-MFF-SynQ^AB/F: 0.5367 -> 0.7498Improved
train on 1500 pairs instead of 150 (ablation)UMF-LUT · UHD-MFF-SynQ^AB/F: 0.5400 -> 0.7498Improved
train on native 4K data instead of low-resolution data (ablation)UMF-LUT · UHD-MFF-SynQ^AB/F: 0.6129 -> 0.7498Improved
use unsupervised loss instead of supervised loss (ablation)UMF-LUT · UHD-MFF-SynQ^AB/F: 0.7491 -> 0.7498No clear effect
use UMF-LUT instead of CCSR-NetUHD-MFF-Syn fusion · UHD-MFF-SynSD: 49.8757 -> 49.9062Improved
use UMF-LUT instead of TC-MoAUHD-MFF-Syn fusion · UHD-MFF 4K efficiencytest time (ms): 5714.91 -> 11.03Improved

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