WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909599628525568 |
|---|---|
| author | Zhang, Daoan Jiang, Che Xu, Ruoshi Chen, Biaoxiang Jin, Zijian Lu, Yutian Zhang, Jianguo Yong, Liang Luo, Jiebo Luo, Shengda |
| author_facet | Zhang, Daoan Jiang, Che Xu, Ruoshi Chen, Biaoxiang Jin, Zijian Lu, Yutian Zhang, Jianguo Yong, Liang Luo, Jiebo Luo, Shengda |
| contents | Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing semantically accurate, coherent, and contextually appropriate images in real-world scenarios. To address this gap, we introduce \textbf{WorldGenBench}, a benchmark designed to systematically evaluate T2I models' world knowledge grounding and implicit inferential capabilities, covering both the humanities and nature domains. We propose the \textbf{Knowledge Checklist Score}, a structured metric that measures how well generated images satisfy key semantic expectations. Experiments across 21 state-of-the-art models reveal that while diffusion models lead among open-source methods, proprietary auto-regressive models like GPT-4o exhibit significantly stronger reasoning and knowledge integration. Our findings highlight the need for deeper understanding and inference capabilities in next-generation T2I systems. Project Page: \href{https://dwanzhang-ai.github.io/WorldGenBench/}{https://dwanzhang-ai.github.io/WorldGenBench/} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_01490 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation Zhang, Daoan Jiang, Che Xu, Ruoshi Chen, Biaoxiang Jin, Zijian Lu, Yutian Zhang, Jianguo Yong, Liang Luo, Jiebo Luo, Shengda Computer Vision and Pattern Recognition Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing semantically accurate, coherent, and contextually appropriate images in real-world scenarios. To address this gap, we introduce \textbf{WorldGenBench}, a benchmark designed to systematically evaluate T2I models' world knowledge grounding and implicit inferential capabilities, covering both the humanities and nature domains. We propose the \textbf{Knowledge Checklist Score}, a structured metric that measures how well generated images satisfy key semantic expectations. Experiments across 21 state-of-the-art models reveal that while diffusion models lead among open-source methods, proprietary auto-regressive models like GPT-4o exhibit significantly stronger reasoning and knowledge integration. Our findings highlight the need for deeper understanding and inference capabilities in next-generation T2I systems. Project Page: \href{https://dwanzhang-ai.github.io/WorldGenBench/}{https://dwanzhang-ai.github.io/WorldGenBench/} |
| title | WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.01490 |