AI Paper Atlas

Research map / Image generation / Editing and style transfer

SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer

Zerui Gong, Zhonghua Wu, Qingyi Tao, Qinyue Li, Chen Change Loy

ICCV 2025 · Image generation › Editing and style transfer · approach: Arbitrary neural style transfer · 6 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 Context Generator (4D LUT) instead of standard 3D LUT (ablation)SA-LUT · PST50LPIPS: 0.14 -> 0.12Improved
add Context Generator (4D LUT) instead of standard 3D LUT (ablation)SA-LUT · PST50H-Corr: 0.38 -> 0.51Improved
add cross-attention between content and style for context map (ablation)SA-LUT · PST50LPIPS: 0.13 -> 0.12Improved
add cross-attention between content and style for context map (ablation)SA-LUT · PST50H-Corr: 0.46 -> 0.51Improved
use 64 basis LUTs instead of 32 (ablation)SA-LUT · PST50H-Corr: 0.41 -> 0.51Improved
increase basis LUTs from 64 to 128 (ablation)SA-LUT · PST50H-Corr: 0.51 -> 0.47Hurt
increase basis LUTs from 64 to 256 (ablation)SA-LUT · PST50H-Corr: 0.51 -> 0.39Hurt
add real-style adversarial stream to synthetic-only training (ablation)SA-LUT · PST50H-Corr: 0.44 -> 0.51Improved
add synthetic stream to real-style-only training (ablation)SA-LUT · PST50LPIPSImproved
SA-LUT versus NLUT LUT generationLUT-based style transfer · PST50LUT generation time (s): 16.1112 -> 0.2128Improved
SA-LUT versus NLUT perceptual distanceLUT-based style transfer · PST50LPIPS: 0.36 -> 0.12Improved

Later papers that compared with this method

5 later accepted papers report SA-LUT as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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