AI Paper Atlas

Research map / Image generation / Image restoration

Real-Time Image Enhancer via Learnable Spatial-Aware 3D Lookup Tables

Tao Wang, Yong Li, Jingyang Peng, Yipeng Ma, Xian Wang, Fenglong Song, Youliang Yan

ICCV 2021 · Image generation › Image restoration · approach: Image harmonization and color transformation · 89 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
increase basic LUTs from 3 to 30 in original 3DLUT (ablation)3DLUT · HDR+ 480p (ours)PSNR: 19.91 -> 20.29Improved
replace the original predictor with our predictor (1D weight only, 30 LUTs) (ablation)3DLUT(30,0) · HDR+ 480p (ours)PSNR: 20.29 -> 20.38Improved
add 3D pixel-wise weight map with spatial-aware LUTs (ablation)Ours(30,0) · HDR+ 480p (ours)PSNR: 20.38 -> 22.52Improved
add 1D scenario weight (T=3) to the 3D weight head, M=10 (ablation)Ours(0,30) · HDR+ 480p (ours)PSNR: 22.52 -> 22.73Improved
full two-head spatial-aware model versus original 3DLUT (ablation)Ours(3,10) · HDR+ 480p (ours)PSNR: 19.91 -> 22.73Improved
increase number of categories M from 1 up to 10 (ablation)spatial-aware 3D LUTs · HDR+ 480p (ours)PSNRImproved
increase M beyond 10 (ablation)spatial-aware 3D LUTs · HDR+ 480p (ours)PSNRNo clear effect
run at 4K full resolution instead of 480p (ablation)Ours(3,10) · HDR+ ablationPSNR: 22.73 -> 22.56Hurt
remove first and last resize in weight predictor (ablation)Ours(3,10) 4K · HDR+ ablationPSNR: 22.56 -> 22.65Improved
add color difference loss to basic loss (ablation)Ours(3,10) · HDR+ (ours)PSNR: 22.54 -> 22.61Improved
add perceptual loss to basic loss (ablation)Ours(3,10) · HDR+ (ours)LPIPS: 0.1906 -> 0.1470Improved
add both color and perceptual losses to basic loss (ablation)Ours(3,10) · HDR+ (ours)PSNR: 22.54 -> 22.73Improved

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