AI Paper Atlas

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

Semantic Line Diffusion: Character-Consistent Line Art from text-annotated Storyboards

Seo-Yeon Choi, Kyungsu Lee

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 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
add multi-reference conditioning (ablation)PanelDiff · Ablation, 50-cut sequencesMS-SSIM: 0.861 -> 0.903Improved
add multi-reference conditioning (ablation)PanelDiff · Ablation, 50-cut sequencesidentity drift: 0.301 -> 0.214Improved
use multiple references instead of single reference (ablation)PanelDiff · Ablation, 50-cut sequencesMS-SSIM: 0.878 -> 0.903Improved
add memory bank (ablation)PanelDiff · Ablation, 50-cut sequencesidentity drift: 0.332 -> 0.214Improved
add memory bank (ablation)PanelDiff · Ablation, 50-cut sequencesMS-SSIM: 0.842 -> 0.903Improved
use full memory instead of recent-only memory (ablation)PanelDiff · Ablation, 50-cut sequencesidentity drift: 0.259 -> 0.214Improved
add similarity interpreter (ablation)PanelDiff · Ablation, 50-cut sequencesidentity drift: 0.317 -> 0.214Improved
add similarity interpreter (ablation)PanelDiff · Ablation, 50-cut sequencesMS-SSIM: 0.851 -> 0.903Improved
increase static references K from 1 to 8 (ablation)PanelDiff · Reference count sweepMS-SSIM: 0.78 -> 0.88Improved
increase static references K from 1 to 8 (ablation)PanelDiff · Reference count sweepidentity drift: 0.32 -> 0.26Improved
increase conti perturbation noise from 0.0 to 1.0PanelDiff · RobustnessMS-SSIM: 0.90 -> 0.79Hurt
increase conti perturbation noise from 0.0 to 1.0Baseline average · RobustnessMS-SSIM: 0.82 -> 0.48Hurt

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