AI Paper Atlas

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

PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation

Yuheng Feng, Wen Zhang, Haodong Duan, Xingxing Zou

CVPR 2026 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 3 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
use closed commercial MLLMs instead of open-source MLLMsposter understanding · PosterIQ understanding averageAverage score: Gemini-2.5-Pro 0.647 vs Qwen3-VL-8B 0.543Improved
use MLLMs as automatic poster quality ratersall evaluated MLLMs · Overall ratingcosine similarity to human ratings: best 0.483 (Gemma 3N-E4B-IT); GPT-5 0.347Hurt
move from simple to hard OCR conditionsMLLMs · Hard OCR vs Simple OCRword recall: GPT-5 0.965 -> 0.496; Grok-4-fast 0.769 -> 0.044Hurt
Qwen family shows stable performance under heavy visual interferenceQwen3-VL-8B · Hard OCRword recall: 0.781 vs GPT-5 0.496Improved
font matching without font-name priorsopen-source MLLMs · Font Matchingnormalized score: near 0 (e.g. MiniCPM-V-4.5 -0.001)Hurt
larger Qwen3-VL (8B vs 4B)Qwen3-VL · Style understandingscore: 0.805 -> 0.610Hurt
larger Qwen3-VL (8B vs 4B)Qwen3-VL · Text localizationmean IoU: 0.223 -> 0.450Improved
closed models for layout generationGemini-2.5-Pro · Layout GenerationArea Ratio: 0.569 vs open best 0.394Improved
compare generators on font generationimage generators · Font generationrichness: best 0.391 vs composition up to 0.866Hurt
iteratively add VLM feedback to revise prompts for a T2I generator (ablation)GPT-Image-1 and Qwen-Image with GPT-5 / Qwen3-VL · Qualitative poster generationposter quality (qualitative)Improved

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