Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.24078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910070987554816 |
|---|---|
| author | Feng, Yuheng Zhang, Wen Duan, Haodong Zou, Xingxing |
| author_facet | Feng, Yuheng Zhang, Wen Duan, Haodong Zou, Xingxing |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24078 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation Feng, Yuheng Zhang, Wen Duan, Haodong Zou, Xingxing Computer Vision and Pattern Recognition 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. |
| title | PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.24078 |