AI Paper Atlas

Research map / Image generation / Image restoration

Joint Demosaicing and Deghosting of Time-Varying Exposures for Single-Shot HDR Imaging

Jungwoo Kim, Min H. Kim

ICCV 2023 · Image generation › Image restoration · approach: Reflection removal · 19 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
replace self-attention with exposure alignment (EA) in the transformer block (ablation)baseline HDR feature registration · Synthetic quad-Bayer testPSNR: 43.98 -> 46.81Improved
add multi-scale (MS) arrangement (ablation)baseline (SA) · Synthetic quad-Bayer testPSNR: 43.98 -> 44.26Improved
add feature extraction (FE) module (ablation)baseline (SA) · Synthetic quad-Bayer testPSNR-mu: 36.99 -> 38.29Improved
add multi-scale to EA (ablation)EA · Synthetic quad-Bayer testPSNR: 46.81 -> 47.57Improved
add feature extraction to EA + MS (full model) (ablation)EA + MS · Synthetic quad-Bayer testPSNR: 47.57 -> 47.89Improved
add feature extraction to EA (ablation)EA · Synthetic quad-Bayer testPSNR: 46.81 -> 46.74No clear effect
joint demosaicing and deghosting with exposure alignment versus deghosting baselinesOurs · Synthetic quad-Bayer testHDR-VDP-2: 72.78 -> 75.57 (vs Liu et al.)Improved

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