AI Paper Atlas

Research map / Image generation / Image restoration

MESS: Multi-Exposure Sequence Synthesis for Generalizable Image Enhancement

Ruodai Cui, Shuaizheng Liu, Rongyuan Wu, Lei Zhang

NeurIPS 2026 · Image generation › Image restoration · approach: Low-light image enhancement · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes MESS, a method for synthesizing multi-exposure image sequences to create large-scale, diverse training data for generalizable image enhancement under adverse illumination.

Problem

Existing image enhancement models (low-light enhancement, exposure correction, backlit enhancement) generalize poorly across scenarios, largely because training requires expensive, manually captured, precisely aligned image pairs that are scarce and limited in diversity.

Approach

Synthesizes multi-exposure image sequences to supply large-scale, diverse training data for enhancement tasks instead of relying on manually captured aligned pairs. Full method details are not available from the abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on MESS-generated data instead of in-domain real datasetsFourLLIE · 5 enhancement test setsPSNR (average): 19.965 -> 21.923 (vs SICE)Improved
train on MESS-generated data instead of RAW-synthesized MSEC dataFourLLIE · 5 enhancement test setsPSNR (average): 20.079 -> 21.923Improved
train on MESS data instead of RGB-synthesized UEC-based dataFourLLIE · 5 enhancement test setsPSNR (average): 19.645 -> 21.923Improved
train on MESS data instead of in-domain data on its own test setFourLLIE · UHDLL, SICEPSNR: 23.694 -> 23.416 (UHDLL); 22.385 -> 21.769 (SICE)Hurt
scale MESS training set from 5K to 500K pairs (ablation)FourLLIE · 5 test sets averagePSNR: 20.220 -> 21.923Improved
train on 5K MESS pairs instead of real LSRW/SICE of similar size (ablation)FourLLIE · 5 test sets averagePSNR: 19.965 -> 20.220Improved
replace RAW-only training data with MESS-RGB data of matched size (ablation)FourLLIE · 5 test sets averagePSNR: 20.764 -> 21.083Improved
remove frequency-based enhancement, diffusion detail, exposure conditioning or representation consistency loss (ablation)MESS generator · downstream FourLLIE, 5 test sets averageFR/NR metricsImproved
use DWT instead of FFT for frequency modeling (ablation)MESS generator · downstream FourLLIEFR/NR metricsImproved
inject exposure via DWT-FiLM and content descriptors instead of plain concatenation or no condition (ablation)MESS renderer · downstream FourLLIEFR/NR metricsImproved

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