AI Paper Atlas

Research map / Image generation / Image restoration

Learned Image Enhancement via Color Naming

David Serrano-Lozano, Luis Herranz, Michael S Brown, Javier Vazquez-Corral

ECCV 2024 · Image generation › Image restoration · approach: Low-light image enhancement

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 color-naming maps to the Bezier control point estimator features (ablation)NamedCurves · MIT-5K DPEPSNR: +0.32 dB PSNR, +0.43 Delta E00Improved
weight the final fusion average with color-naming maps (ablation)NamedCurves · MIT-5K DPEPSNR: +0.31 dB PSNR, +0.32 Delta E00Improved
add attention-based local modification before fusion (ablation)NamedCurves · MIT-5K DPEPSNR: 24.56 -> 24.68Improved
use the proposed backbone instead of UNet, LPIENet or TED (ablation)NamedCurves · MIT-5K DPEPSNR: 24.70 -> 24.91Improved
use 11 Bezier control points instead of 5, 7 or 16 (ablation)NamedCurves · MIT-5K DPEPSNR: 24.52 (16 pts) -> 24.91 (11 pts)Mixed
use NamedCurves with other backbones (ablation)NamedCurves · MIT-5K DPEPSNR: 24.49 -> 24.91Improved
use NamedCurves on images with few dominant colorsNamedCurves · MIT-5K images dominated by two colorsqualitativeHurt
NamedCurves versus AdaInt on PPR10K Expert CNamedCurves · PPR10K Expert CPSNR: 25.68 -> 25.69No clear effect
NamedCurves versus 3D LUT methods at inferenceNamedCurves · MIT-5K 480ptime (ms): 10 (SepLUT) -> 26Hurt

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