T2I-ReasonBench：推理引导文本到图像生成的基准测试
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
August 24, 2025
作者: Kaiyue Sun, Rongyao Fang, Chengqi Duan, Xian Liu, Xihui Liu
cs.AI
摘要
我們提出了T2I-ReasonBench，這是一個評估文本到圖像（T2I）模型推理能力的基準。它包含四個維度：成語理解、文本圖像設計、實體推理和科學推理。我們提出了一個兩階段評估協議來衡量推理準確性和圖像質量。我們對多種T2I生成模型進行了基準測試，並對其性能提供了全面分析。
English
We propose T2I-ReasonBench, a benchmark evaluating reasoning capabilities of
text-to-image (T2I) models. It consists of four dimensions: Idiom
Interpretation, Textual Image Design, Entity-Reasoning and
Scientific-Reasoning. We propose a two-stage evaluation protocol to assess the
reasoning accuracy and image quality. We benchmark various T2I generation
models, and provide comprehensive analysis on their performances.