返回文献探索AI 摘要
Paper · arXiv 2508.17472
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation
Kaiyue Sun, Rongyao Fang, Chengqi Duan, Xian Liu, Xihui Liu
26 upvotesAugust 24, 2025arXiv 预印本
T2I-ReasonBench evaluates the reasoning capabilities of text-to-image models across four dimensions using a two-stage protocol, analyzing their performance comprehensively.
text-to-imageT2IIdiom InterpretationTextual Image DesignEntity-ReasoningScientific-Reasoningtwo-stage evaluation protocol
Abstract
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.