AI Paper Atlas

Research map / Image generation / Editing and style transfer

ReDesign: Recovering Editable Design Structures from Raster Images via Agentic Decomposition

Jooyeol Yun, Jintae Park, Hyesu Lim, Junha Hyung, Hyungjin Chung, Choo Jaegul

ECCV 2026 · Image generation › Editing and style transfer · approach: Localized and attribute-specific editing

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 lineal memory (ablation)ReDesign · Figma (subset)PQ: 39.09 -> 44.76Improved
add lineal memory (ablation)ReDesign · Figma (subset)L1: 0.0542 -> 0.0474Improved
use parallel tree expansion instead of sequential execution (ablation)ReDesign · Figma (subset)PQ: 42.00 -> 44.76Improved
use parallel tree expansion instead of sequential execution (ablation)ReDesign · Figma (subset)Tool calls: 36.8 -> 28.8Improved
increase tree depth from 2 to full depth (ablation)ReDesign · Figma (subset)PQ: 31.92 -> 44.76Improved
increase tree depth from 2 to full depth (ablation)ReDesign · Figma (subset)PSNR: 28.43 -> 25.56Hurt
increase tree depth from 3 to full depth (ablation)ReDesign · Figma (subset)F1: 0.4939 -> 0.5194Improved
increase tree depth from 3 to full depth (ablation)ReDesign · Figma (subset)API cost: $0.020 -> $0.027Hurt
replace Gemini-3 flash with GPT-5 mini as controller (ablation)ReDesign · Figma (909 files)PQ: 45.37 -> 43.39Mixed
use stepwise graceful verification instead of terminal verificationReDesign · Figma (909 files)PSNR and timeImproved
use tree-structured parallel expansion instead of serial tool useReDesign · Figma (909 files)speedup: 7.1x speedupImproved
use hierarchical expansion with verification instead of linear tool chainReDesign vs Tool Agent · Figma (909 files)PSNR: 13.923 -> 26.286Improved

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