Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation

Yuheng Feng, Wen Zhang, Haodong Duan, Xingxing Zou

Abstract

We present PosterIQ, a design-driven benchmark for poster understanding and generation, annotated across composition structure, typographic hierarchy, and semantic intent. It includes 7,765 image-annotation instances and 822 generation prompts spanning real, professional, and synthetic cases. To bridge visual design cognition and generative modeling, we define tasks for layout parsing, text-image correspondence, typography/readability and font perception, design quality assessment, and controllable, composition-aware generation with metaphor. We evaluate state-of-the-art MLLMs and diffusion-based generators, finding persistent gaps in visual hierarchy, typographic semantics, saliency control, and intention communication; commercial models lead on high-level reasoning but act as insensitive automatic raters, while generators render text well yet struggle with composition-aware synthesis. Extensive analyses show PosterIQ is both a quantitative benchmark and a diagnostic tool for design reasoning, offering reproducible, task-specific metrics. We aim to catalyze models' creativity and integrate human-centred design principles into generative vision-language systems.

PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation

Abstract

We present PosterIQ, a design-driven benchmark for poster understanding and generation, annotated across composition structure, typographic hierarchy, and semantic intent. It includes 7,765 image-annotation instances and 822 generation prompts spanning real, professional, and synthetic cases. To bridge visual design cognition and generative modeling, we define tasks for layout parsing, text-image correspondence, typography/readability and font perception, design quality assessment, and controllable, composition-aware generation with metaphor. We evaluate state-of-the-art MLLMs and diffusion-based generators, finding persistent gaps in visual hierarchy, typographic semantics, saliency control, and intention communication; commercial models lead on high-level reasoning but act as insensitive automatic raters, while generators render text well yet struggle with composition-aware synthesis. Extensive analyses show PosterIQ is both a quantitative benchmark and a diagnostic tool for design reasoning, offering reproducible, task-specific metrics. We aim to catalyze models' creativity and integrate human-centred design principles into generative vision-language systems.
Paper Structure (17 sections, 15 equations, 28 figures, 7 tables)

This paper contains 17 sections, 15 equations, 28 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Multimodal Benchmarks
  4. Poster Design and Generative Models
  5. Benchmark
  6. Understanding Tasks
  7. Generation Tasks
  8. Experiment
  9. Understanding Task
  10. Generation Task
  11. Conclusion
  12. Benchmark Statistics
  13. Task Evaluation
  14. Human Evaluation
  15. Annotator Guideline
  16. ...and 2 more sections

Figures (28)

  • Figure 1: Overview of the benchmark, which includes over a dozen tasks
  • Figure 2: Qualitative comparison of four models on three layout-related tasks. For Text Localization and Layout Generation, the predicted bounding boxes are shown in red. For the Empty Space task, the selected patch IDs are highlighted in the image.
  • Figure 3: Qualitative comparison of four models on five generation tasks.
  • Figure 4: Qualitative comparison of model outputs over supervision-guided iterations.
  • Figure 5: Benchmark statistics for understanding tasks (top) and generation tasks (bottom).
  • ...and 23 more figures