发表机构
ZTE Corporation（中兴通讯）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出基于构图的COMEX基准与SFT+GRPO两阶段框架，用于可解释美学图像裁剪，通过多组实验验证了框架的有效性与可迁移性。
AI 中文摘要
可解释美学图像裁剪不仅需要定位视觉美观的裁剪区域，还需解释该区域受偏好的原因。现有“裁剪并解释”方法大多将解释视为事后文本生成，忽视了构图这一关键美学因素，而构图是连接裁剪决策与可解释推理的核心。本文将可解释美学图像裁剪重新表述为结构化的“裁剪-构图-解释”问题。为支撑该设定，我们引入COMEX这一新型基准，通过图像扩展与IO反转流水线构建而成，包含33161个四元组，每个四元组由扩展图像、裁剪框、构图类别及基于构图的解释组成，可实现裁剪定位、构图理解与解释生成的联合学习。我们进一步提出两阶段SFT+GRPO框架：监督微调（Supervised Fine-Tuning，SFT）建立结构化输出协议与基础裁剪能力，GRPO则进一步提升裁剪质量、构图预测及解释的忠实度。我们在COMEX上对15个大型视觉-语言模型及现有裁剪方法进行基准测试，构建了基于构图的可解释美学裁剪的综合测试平台。在COMEX及现有基准上的实验均证明了我们框架的有效性与可迁移性，在各项评估指标上表现优异。
英文摘要
Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred. Existing crop-and-explain methods largely treat explanation as post-hoc text generation and overlook composition, a key aesthetic factor that links crop decisions with interpretable reasoning. In this paper, we reformulate explainable aesthetic image cropping as a structured crop-composition-explanation problem. To support this setting, we introduce COMEX, a new benchmark built through image expansion and an IO-reversal pipeline. COMEX contains 33,161 quadruples, each consisting of an expanded image, a crop box, a composition category, and a composition-grounded explanation, enabling joint learning of crop localization, composition understanding, and explanation generation. We further propose a two-stage SFT+GRPO framework, where supervised fine-tuning establishes the structured output protocol and basic cropping ability, and GRPO further improves crop quality, composition prediction, and explanation faithfulness. We benchmark 15 large vision-language models and existing cropping methods on COMEX, establishing a comprehensive testbed for composition-grounded explainable aesthetic cropping. Experiments on both COMEX and prior benchmarks demonstrate the effectiveness and transferability of our framework, with strong performance across evaluation metrics.
