从成对用户偏好中学习个性化摄影风格
Learning Personalized Photographic Style from Pairwise User Preferences
提供了以成对比较标注刻画用户隐式审美偏好的数据与评测协议，可复用于个性化图像增强、风格迁移与生成模型的用户对齐；其比较式评估框架也适用于其他主观视觉任务（如审美评分、个性化生成）的评测设计。
原文依据 we introduce PPSD, a dataset containing pairwise preference judgments from 767 users, each providing an average of 70 comparisons
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论摄影风格偏好极具个人色彩，个体之间在色彩与影调审美上存在差异。我们提出个性化摄影风格（PPS）学习，其目标是从比较判断中捕捉用户的隐式偏好，并将其一致地应用于多样化的图像。为给该问题奠定基础，我们给出三项贡献。第一，我们提出 PPSD，一个包含来自 767 名用户的成对偏好判断的数据集，每位用户平均提供 70 次比较。为捕捉多样的风格信号，图像来源于专业修图、设备成像管线以及生成模型。第二，我们探索了若干基线模型，证明了将风格迁移与增强方法适配于偏好学习的可行性。第三，我们构建了一个适合个人偏好隐式特性的比较式评测框架。我们将公开该数据集，并希望本工作能为推进个性化摄影风格学习的研究奠定基础。
英文原文摘要 1055 字符
Photographic style preferences are deeply personal, varying across individuals in color and tonal aesthetics. We introduce Personalized Photographic Style (PPS) learning, where the goal is to capture a user's implicit preferences from comparative judgments and apply them consistently across diverse images. To establish a foundation for this problem, we present three contributions. First, we introduce PPSD, a dataset containing pairwise preference judgments from 767 users, each providing an average of 70 comparisons. To capture diverse style signals, images are sourced from professional edits, device pipelines, and generative models. Second, we explore several baseline models demonstrating the feasibility of adapting style transfer and enhancement approaches for preference learning. Third, we develop a comparative evaluation framework suited to the implicit nature of personal preferences. We will make our dataset publicly available, and hope this work serves as a foundation for advancing research in personalized photographic style learning.