atlas

Research map / Image generation / Image restoration

Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset

CVPR 2023 · Image generation › Image restoration · approach: Pansharpening and spectral fusion · 37 citations (OpenAlex)

Read the paperCheck 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 pyramid cross-attention alignment and joint HDR denoising/fusion instead of HDR-TransformerHDR reconstruction on Mobile-HDR · Mobile-HDR test set, raw PSNR-lPSNR-l: 35.42 -> 36.37Helped
add pyramid cross-attention alignment (ablation)Joint-HDRDN · Mobile-HDR test set, rawPSNR-l: 35.26 -> 36.37Helped
add attention transfer to pyramid cross-attention alignment (ablation)Joint-HDRDN · Mobile-HDR test set, rawPSNR-l: 36.00 -> 36.37Helped
add attention fusion after alignment (ablation)Joint-HDRDN · Mobile-HDR test set, rawPSNR-µ: 38.71 -> 38.92Helped
train on Mobile-HDR rather than Sig17 DSLR dataHDR-Transformer · Mobile-HDR test set, sRGBPSNR-l: 23.59 -> 36.67Helped
train on Mobile-HDR rather than Sig17 DSLR dataJoint-HDRDN · Mobile-HDR test set, sRGBPSNR-l: 23.45 -> 37.46Helped

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