AI Paper Atlas

Research map / Image generation / Image restoration

Attention-Guided Network for Ghost-Free High Dynamic Range Imaging

CVPR 2019 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 312 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 attention-guided feature merging instead of directly stacking non-reference features (ablation)AHDRNet · Kalantari dataset testPSNR-μHelped
use dilated convolutions in the residual dense blocks (ablation)AHDRNet · Kalantari dataset testPSNRHelped
use dense residual connections instead of residual blocks (ablation)AHDRNet · Kalantari dataset testHDR image qualityHelped
increase residual-block depth without dense connections or dilation (ablation)AHDRNet · Kalantari dataset testghosting artifactsNo clear effect
add global residual learning from the reference features (ablation)AHDRNet · Kalantari dataset testperformanceHelped
use ℓ1 loss instead of ℓ2 loss (ablation)AHDRNet · Kalantari dataset testPSNR-μ: 43.0630 -> 43.6172Helped
add optical-flow alignment preprocessingAHDRNet · Kalantari dataset testPSNR-μ: 43.6172 -> 43.9764Helped
add optical-flow alignment preprocessingAHDRNet · Kalantari dataset testPSNR-M: 33.0429 -> 32.7785Hurt

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