AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Wasserstein Style Distribution Analysis and Transform for Stylized Image Generation

Xi Yu, Xiang Gu, Zhihao Shi, Jian Sun

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 0 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
raise threshold tau from 0.0 to 0.2 (transform style-relevant channels) (ablation)WSDT · StyleDrop and InstaStyle evaluation setsStyle Score: 0.476 -> 0.546Improved
raise threshold tau from 0.0 to 0.2 (ablation)WSDT · StyleDrop and InstaStyle evaluation setsContent Score: 0.298 -> 0.285Hurt
raise tau from 0.2 to 0.4 (ablation)WSDT · StyleDrop and InstaStyle evaluation setsStyle Score: 0.546 -> 0.546No clear effect
raise tau from 0.2 to 0.4 (ablation)WSDT · StyleDrop and InstaStyle evaluation setsContent Score: 0.285 -> 0.283Hurt
transform all channels instead of adaptive selection (tau 0.2) (ablation)WSDT · StyleDrop and InstaStyle evaluation setsContent Score: 0.285 -> 0.281Hurt
transform all channels instead of adaptive selection (tau 0.2) (ablation)WSDT · StyleDrop and InstaStyle evaluation setsStyle Score: 0.546 -> 0.547No clear effect
use WSDT instead of the strongest baseline StyleAlignedSDXL · StyleDrop and InstaStyle evaluation setsGM Metric: 10.53 -> 5.52Improved
use WSDT instead of VSPSDXL · StyleDrop and InstaStyle evaluation setsUser Preference: 0.246 -> 0.494Improved
use WSDT instead of StyleAlignedSDXL · StyleDrop and InstaStyle evaluation setsStyle Score: 0.538 -> 0.546Improved
use WSDT instead of VSPSDXL · StyleDrop and InstaStyle evaluation setsContent Score: 0.282 -> 0.285Improved
apply AdaIN on noisy latents instead of WSDT feature transform (ablation)SDXL · qualitativestyle alignmentHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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