AI Paper Atlas

Research map / Image generation / Image restoration

ExpoMotion: A Large-Scale Benchmark and A Householder Projection Network for Multi-Exposure Fusion

Yao Liu, Lishen Qu, Jie Liang, shihao zhou, Hui Zeng, Yabin Peng, Huipeng Lin, Lei Zhang, Jufeng Yang

ECCV 2026 · Image generation › Image restoration · approach: Reflection removal · 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 GPIA (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 27.8562Improved
add HOPU (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 27.9003Improved
replace GDFN with GGFN (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 27.8332Improved
add HOPU and GGFN together (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 28.2321Improved
add GPIA and GGFN together (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 28.1334Improved
add all three modules GPIA, HOPU, GGFN (ablation)HOP-S baseline · Kalantari17PSNR (dB): 27.4526 -> 28.5011Improved
add all three modules (parameter cost) (ablation)HOP-S baseline · Kalantari17Params (M): 3.3818 -> 3.6990Hurt
scale HOP-S to HOP-BHOP · Kalantari17PSNR (dB): 28.501 -> 28.804Improved
use HOP-B instead of RestormerRestormer · Kalantari17Params (M): 26.10 -> 15.69Improved
train on ExpoMotion instead of Kalantari17HOP-B · Sen+TursenMUSIQ: 57.87 -> 62.74Improved
train on ExpoMotion instead of RealHDRVHOP-B · Sen+TursenMUSIQ: 60.89 -> 62.74Improved
use HOP-B instead of Restormer (same ExpoMotion training data)Restormer · Sen+TursenMUSIQ: 62.32 -> 62.74Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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