AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

EvaNet: Toward More Efficient and Consistent Infrared and Visible Image Fusion Assessment

Chunyang Cheng, Tianyang Xu, Xiao‐Jun Wu, Tao Zhou, Hui Li, Zhangyong Tang, Josef Kittler

TPAMI 2026 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 1 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 environment perception branch (ablation)EvaNet · LLVIPavg metric consistency change vs (a): 7.47% -> 8.70%Improved
add contrastive learning during training (ablation)EvaNet · LLVIPavg metric consistency change vs (a): -0.80% -> 8.70%Improved
add decomposition module (ablation)EvaNet · LLVIPavg metric consistency change vs (a): 2.16% -> 8.70%Improved
use EvaNet to enhance vanilla metricsQabf · LLVIPMC_deep: 0.611 -> 0.717Improved
use EvaNet to enhance vanilla metricsFMI_d · LLVIPMC_deep: 0.713 -> 0.640Hurt
use EvaNet to enhance VIFVIF · RoadSceneMC_deep: 0.753 -> 0.629Hurt
add TextAttn textual guidance to vanilla metricsSSIM · LLVIPMC_deep: 0.649 -> 0.560Hurt
use EvaNet to enhance vanilla metricsVIF · LLVIP detectionMC_ds: 0.590 -> 0.752Improved
use EvaNet to enhance vanilla metricsPSNR · LLVIP detectionMC_ds: 0.775 -> 0.717Hurt
jointly predict more related metrics (N=6 to N=8) (ablation)EvaNet · LLVIPMC_deep FMI_dImproved
replace human environment labels with LLM-generated ones (ablation)EvaNet · LLVIPMC_deepImproved
use EvaNet instead of 8 traditional metric executionsEvaNet · LLVIP-test (part)time (s): 7694.3s -> 1.6sImproved

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