AI Paper Atlas

Research map / Image generation / Editing and style transfer

VecDesigner: Exploring Visual Guidance and Structural Consistency for Semantic Typography

Liu Yu, Xingjiao Wu, Ziang Liu, Jiabao Zhao, Daoguo Dong, Liang He

ICML 2026 · Image generation › Editing and style transfer · approach: Texture and sketch synthesis

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 VGSDS visual guidance to vanilla SDS (ablation)vanilla SDS baseline · Semantic typography (100 concepts, 5 fonts)OCR accuracy (%): 81.26 -> 83.55Improved
add Procrustes loss to VGSDS (ablation)VGSDS · Semantic typography (100 concepts, 5 fonts)Chamfer distance: 1.4816 -> 1.4495Improved
add intersection loss to VGSDS + Procrustes (ablation)VGSDS + Procrustes · Semantic typography (100 concepts, 5 fonts)Chamfer distance: 1.4495 -> 1.3717Improved
add VGSDS to Procrustes + intersection loss (ablation)VecDesigner · Semantic typography (100 concepts, 5 fonts)OCR accuracy (%): 84.33 -> 85.36Improved
add Procrustes loss to VGSDS + intersection loss (ablation)VecDesigner · Semantic typography (100 concepts, 5 fonts)BLIPScore: 0.3467 -> 0.3535Improved
update reference images every 500 steps instead of 50 (ablation)VecDesigner · Semantic typography (100 concepts, 5 fonts)OCR accuracy (%): 83.21 -> 85.36Improved
update reference images every 500 steps instead of 100 (ablation)VecDesigner · Semantic typography (100 concepts, 5 fonts)Chamfer distance: 1.4455 -> 1.3717Improved
use 10 additional sampling points instead of none (ablation)Procrustes loss · Semantic typography (100 concepts, 5 fonts)OCR accuracy (%): 84.08 -> 85.36Improved
use 10 additional sampling points instead of 20 (ablation)Procrustes loss · Semantic typography (100 concepts, 5 fonts)CLIPScore: 0.2733 -> 0.2688Hurt
vary lambda_v, lambda_p, lambda_s (ablation)VecDesigner · Semantic typography (100 concepts, 5 fonts)all metricsNo clear effect
use VecDesigner instead of Word-As-Imagevector-based semantic typography · Semantic typography (100 concepts, 5 fonts)CLIPScore: 0.2518 -> 0.2733Improved
use VecDesigner instead of Word-As-Imagevector-based semantic typography · Semantic typography (100 concepts, 5 fonts)OCR accuracy (%): 82.36 -> 85.36Improved

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