R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
This addresses the need for better evaluation of reasoning in text-to-image generation for AI researchers and developers, though it is incremental as it focuses on benchmarking rather than proposing new methods.
The authors tackled the problem of evaluating reasoning capabilities in text-to-image generation by introducing R2I-Bench, a comprehensive benchmark with curated data across multiple reasoning categories, and found that 16 representative models showed consistently limited performance, highlighting deficiencies in current systems.
Reasoning is a fundamental capability often required in real-world text-to-image (T2I) generation, e.g., generating ``a bitten apple that has been left in the air for more than a week`` necessitates understanding temporal decay and commonsense concepts. While recent T2I models have made impressive progress in producing photorealistic images, their reasoning capability remains underdeveloped and insufficiently evaluated. To bridge this gap, we introduce R2I-Bench, a comprehensive benchmark specifically designed to rigorously assess reasoning-driven T2I generation. R2I-Bench comprises meticulously curated data instances, spanning core reasoning categories, including commonsense, mathematical, logical, compositional, numerical, causal, and concept mixing. To facilitate fine-grained evaluation, we design R2IScore, a QA-style metric based on instance-specific, reasoning-oriented evaluation questions that assess three critical dimensions: text-image alignment, reasoning accuracy, and image quality. Extensive experiments with 16 representative T2I models, including a strong pipeline-based framework that decouples reasoning and generation using the state-of-the-art language and image generation models, demonstrate consistently limited reasoning performance, highlighting the need for more robust, reasoning-aware architectures in the next generation of T2I systems. Project Page: https://r2i-bench.github.io