超越绝对分数：基于编辑诱导差异的通用图像美学评估
Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment
AI总结：
提出RED-Aes框架，利用可控图像编辑模型模拟人类审美推理，通过相对编辑诱导差异学习通用美学原则，实现跨场景泛化。
摘要：
传统的图像美学评估（IAA）方法主要依赖于回归绝对平均意见分数（MOS）。然而，这种范式忽视了人类审美感知固有的动态性质，这种感知依赖于对隐含视觉参考的无意识比较。因此，缺乏对美学差异的因果推理使得模型无法学习通用的美学原则，从而限制了它们在多样化场景中的泛化能力。在这项工作中，我们重新思考IAA任务，并提出相对编辑诱导差异美学学习（RED-Aes），一种新颖的框架，利用可控图像编辑模型模拟人类审美推理过程。RED-Aes不拟合绝对分数分布，而是显式学习驱动美学变化的视觉因素。为了支持这一范式，我们构建了RED-20k数据集，包含基于编辑的图像对、定量美学差异和思维链（CoT）推理。此外，我们引入了一种由相对排序一致性奖励引导的三阶段训练策略，仅通过相对监督优化模型。大量实验表明，RED-Aes在多个公共基准上取得了最先进的性能，展现出优越的泛化能力。
英文摘要：
Traditional Image Aesthetic Assessment (IAA) methods mainly rely on regressing absolute Mean Opinion Scores (MOS). However, such a paradigm overlooks the inherently dynamic nature of human aesthetic perception, which relies on subconscious comparison against implicit visual references. Consequently, the lack of causal reasoning regarding aesthetic differences prevents models from learning generalizable aesthetic principles, thus limiting their generalization across diverse scenarios. In this work, we rethink the IAA task and propose Relative Edit-induced Difference Aesthetic learning (RED-Aes), a novel framework that leverages controllable image editing models to simulate the human aesthetic reasoning process. Instead of fitting absolute score distributions, RED-Aes explicitly learns the visual factors that drive aesthetic changes. To support this paradigm, we construct the RED-20k dataset, which comprises editing-based image pairs, quantitative aesthetic differences, and Chain-of-Thought (CoT) reasoning. Furthermore, we introduce a three-stage training strategy guided by a relative ranking consistency reward, optimizing the model solely via relative supervision. Extensive experiments demonstrate that RED-Aes achieves state-of-the-art performance on multiple public benchmarks, exhibiting superior generalization capabilities.
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。
