基于反思生成的基准测试与进化
Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
AI总结:
本文提出R^3-Bench基准和R^3-Refiner框架,用于评估和提升反思视觉生成能力,通过改进迭代推理和修正能力,提升文本到图像模型的生成质量。
摘要:
文本到图像(T2I)模型和统一多模态模型(UMMs)在视觉生成领域取得了显著进展。然而,其依赖于单次生成范式限制了处理需要迭代细化的复杂提示的能力。为了实现多轮反思视觉生成(RVG),我们正式将Reason-Reflect-Rectify(R^3)循环作为核心框架,并引入R^3-Bench,一个包含600多个专家标注实例的基准,用于量化迭代推理和修正能力。在R^3-Bench上的评估揭示了一个关键差距:尽管最先进的模型能够识别生成错误,但它们无法生成具有操作性的修正指令。为弥合这一差距,我们提出了R^3-Refiner,一个双阶段框架,利用组相对策略优化(GRPO)和分层奖励机制(HRM)来更好地对齐修正与反思推理。实验表明,R^3-Refiner在R^3-Bench上实现了显著改进(在反思判断分数上提升12.0%,在修正分数上提升9.0%),并且可以无缝集成到各种多语言大型模型(MLLMs)中,以提升不同T2I模型在GenEval++和T2I-CompBench上的生成质量。代码可在https://github.com/xiaomoguhz/R3-Bench获取。
英文摘要:
Text-to-Image (T2I) models and Unified Multimodal Models (UMMs) have achieved remarkable progress in visual generation. However, their reliance on a single-pass generation paradigm limits their ability to handle complex prompts requiring iterative refinement. To enable multi-round Reflective Visual Generation (RVG), we formalize the Reason-Reflect-Rectify (R^3) loop as a core framework and introduce R^3-Bench, a benchmark of over 600 expert-annotated instances that quantifies iterative reasoning and rectification capabilities. Evaluation on R^3-Bench reveals a critical gap: while state-of-the-art models can identify generation errors, they fail to generate actionable rectification instructions. To bridge this gap, we propose R^3-Refiner, a dual-stage framework leveraging Group Relative Policy Optimization (GRPO) and a Hierarchical Reward Mechanism (HRM) to better align rectification with reflective reasoning. Experiments show that R^3-Refiner achieves significant improvements on R^3-Bench (+12.0% in Reflective Verdict Score, +9.0% in Rectification Score), and can be seamlessly integrated with various MLLMs to enhance the generation quality of different T2I models on GenEval++ and T2I-CompBench. Code is available at https://github.com/xiaomoguhz/R3-Bench.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。