AI Paper Atlas

Research map / Image generation / Image restoration

Revisiting Image Fusion for Multi-Illuminant White-Balance Correction

David Serrano-Lozano, Aditya Arora, Luis Herranz, Konstantinos G. Derpanis, Michael S. Brown, Javier Vazquez-Corral

ICCV 2025 · Image generation › Image restoration · approach: Image harmonization and color transformation · 5 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 transformer-based non-linear fusion of five WB presetsDeepWB · Multi-illuminant dataset (Sony+Nikon)mean DeltaE2000: 6.83 -> 4.55Improved
replace linear per-pixel blending with transformer fusionMixedWB · Multi-illuminant dataset (Sony+Nikon)mean DeltaE2000: 9.31 -> 4.55Improved
replace linear blending with transformer fusionStyleWB · Multi-illuminant dataset (Sony split)mean DeltaE2000: 9.46 -> 4.71Improved
use all five WB presets instead of daylight only (ablation)Ours · Multi-illuminant dataset (Sony+Nikon)mean DeltaE2000: 5.47 -> 4.55Improved
use all five presets instead of three (DST) (ablation)Ours · Multi-illuminant dataset (Sony+Nikon)mean DeltaE2000: 5.18 -> 4.55Improved
use all five presets instead of daylight only (ablation)Ours · Multi-illuminant dataset (Sony+Nikon)mean MAE: 4.27 -> 3.61Improved
use linear fusion of presets (MixedWB) instead of standard sRGB WB (DeepWB)DeepWB · Multi-illuminant dataset (Sony+Nikon)mean DeltaE2000: 6.83 -> 9.31Hurt
transformer fusion trained on Nikon, tested on SonyMixedWB · Cross-camera (train Nikon, test Sony)mean DeltaE2000: 9.17 -> 5.80Improved
transformer fusion on synthetic multi-illuminant test setStyleWB · Cross-dataset (Synthetic test set)mean DeltaE2000: 9.90 -> 7.53Improved
transformer fusion on single-illuminant Cube+MixedWB · Cube+ single illuminantDeltaE: 5.03 -> 4.19Improved
transformer fusion with channel-wise transposed attentionDeepWB · inference time, 50 images 500x700runtime: 459 -> 179Improved

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