首个考虑用户审美偏好的图像生成评估框架，让模型更懂你的口味。
PIPBench: A Profile-Inclusive Framework for Personalized Image Generation Evaluation
- 基于用户历史偏好图和短提示，构建个性化生成评估体系
- 通过心理与人口统计学维度，实现真实用户与智能体数据双渠道采集
- 揭示现有方法在个性化生成中的关键缺陷，推动新方向发展
近期文本到图像模型（如 DALL·E 3）虽能响应多样提示，却忽视个体审美偏好。本文研究个性化图像生成任务，即模型需基于少量用户历史偏好图像和简短提示，生成符合其隐式视觉偏好的内容。为此，我们提出 PIPBench——首个面向个性化图像生成的、包含用户画像的基准测试框架。同时设计新颖的数据构建流程，融合心理与人口统计学维度，实现真实用户数据收集与可扩展的代理数据生成。基于 PIPBench，我们对代表性方法进行全面评估，发现现有方法存在显著局限，揭示了个性化文本到图像合成的新挑战与机遇。
原文摘要 · Abstract (English)
Recent text-to-image models such as DALLE-3 excel at following diverse prompts yet remain blind to individual aesthetic preferences. We study personalized image generation, where models must align outputs with a user's implicit visual preferences based on a few historically preferred images and a short prompt. To this end, we introduce PIPBench, the first profile-inclusive benchmark for evaluating personalized image generation. We further propose a novel data construction pipeline that leverages psychological and demographic profiling dimensions for both real-user data collection and scalable agent-based data generation. Using PIPBench, we conduct a thorough evaluation of representative line of methods. Our experiments reveal key limitations in existing methods, suggesting new challenges and opportunities for personalized text-to-image synthesis. Project page: https://wuyuhang05.github.io/PIPBench/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。