Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911475016138752 |
|---|---|
| author | Li, Ouxiang Wang, Yuan Hu, Xinting Huang, Huijuan Chen, Rui Ou, Jiarong Tao, Xin Wan, Pengfei Qi, Xiaojuan Feng, Fuli |
| author_facet | Li, Ouxiang Wang, Yuan Hu, Xinting Huang, Huijuan Chen, Rui Ou, Jiarong Tao, Xin Wan, Pengfei Qi, Xiaojuan Feng, Fuli |
| contents | Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and \textbf{\textit{reasoning}}. Despite recent advances of T2I models in both composition and reasoning, existing benchmarks remain limited in evaluation. They not only fail to provide comprehensive coverage across and within both capabilities, but also largely restrict evaluation to low scene density and simple one-to-one reasoning. To address these limitations, we propose \textbf{\textsc{T2I-CoReBench}}, a comprehensive and complex benchmark that evaluates both composition and reasoning capabilities of T2I models. To ensure comprehensiveness, we structure composition around scene graph elements (\textit{instance}, \textit{attribute}, and \textit{relation}) and reasoning around the philosophical framework of inference (\textit{deductive}, \textit{inductive}, and \textit{abductive}), formulating a 12-dimensional evaluation taxonomy. To increase complexity, driven by the inherent real-world complexities, we curate each prompt with higher compositional density for composition and greater reasoning intensity for reasoning. To facilitate fine-grained and reliable evaluation, we also pair each evaluation prompt with a checklist that specifies individual \textit{yes/no} questions to assess each intended element independently. In statistics, our benchmark comprises 1,080 challenging prompts and around 13,500 checklist questions. Experiments across 38 current T2I models reveal that their composition capability still remains limited in high compositional scenarios, while the reasoning capability lags even further behind as a critical bottleneck, with all models struggling to infer implicit elements from prompts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03516 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play? Li, Ouxiang Wang, Yuan Hu, Xinting Huang, Huijuan Chen, Rui Ou, Jiarong Tao, Xin Wan, Pengfei Qi, Xiaojuan Feng, Fuli Computer Vision and Pattern Recognition Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and \textbf{\textit{reasoning}}. Despite recent advances of T2I models in both composition and reasoning, existing benchmarks remain limited in evaluation. They not only fail to provide comprehensive coverage across and within both capabilities, but also largely restrict evaluation to low scene density and simple one-to-one reasoning. To address these limitations, we propose \textbf{\textsc{T2I-CoReBench}}, a comprehensive and complex benchmark that evaluates both composition and reasoning capabilities of T2I models. To ensure comprehensiveness, we structure composition around scene graph elements (\textit{instance}, \textit{attribute}, and \textit{relation}) and reasoning around the philosophical framework of inference (\textit{deductive}, \textit{inductive}, and \textit{abductive}), formulating a 12-dimensional evaluation taxonomy. To increase complexity, driven by the inherent real-world complexities, we curate each prompt with higher compositional density for composition and greater reasoning intensity for reasoning. To facilitate fine-grained and reliable evaluation, we also pair each evaluation prompt with a checklist that specifies individual \textit{yes/no} questions to assess each intended element independently. In statistics, our benchmark comprises 1,080 challenging prompts and around 13,500 checklist questions. Experiments across 38 current T2I models reveal that their composition capability still remains limited in high compositional scenarios, while the reasoning capability lags even further behind as a critical bottleneck, with all models struggling to infer implicit elements from prompts. |
| title | Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.03516 |