AI 中文总结
FedPAIE框架通过联邦学习在不集中用户私人照片的情况下，实现了个性化图像增强，平衡了用户偏好与图像保真度，效果良好。
AI 中文摘要
个性化图像增强应反映个人审美品味，但学习此类偏好通常依赖私人照片和评分，不适用于集中收集。该任务需从稀疏、异构的反馈中推断偏好，并将其转化为资源受限用户设备上自然的色彩变换。我们提出FedPAIE，这是一种联邦式个性化美学图像增强框架，用于用户自适应调色，无需集中原始照片或评分。FedPAIE训练轻量双线索美学评分器，在小型本地支持集上将其校准为个性化评分器，并冻结该评分器，以从未配对的本地照片指导轻量CLUT增强器的正则化适配。保真度约束和超额间隙惩罚对评分器指导的适配进行正则化，以限制代理评分的过度优化，同时保留内容和自然外观。整个流程的训练保持轻量：评分器学习最多更新0.787M参数，增强器适配更新0.265M，推理仅保留0.293M参数的个性化增强器。在MIT-Adobe FiveK和Flickr-AES上的实验表明，该方法实现了有效的开放世界个性化，且在用户偏好与图像保真度之间取得了良好平衡。FedPAIE因此将分散式偏好学习与高效个性化图像变换相结合，无需配对用户修图。
英文摘要
Personalized image enhancement should reflect individual aesthetic taste, yet learning such preferences commonly depends on private photos and ratings that are unsuitable for centralized collection. The task must infer preference from sparse, heterogeneous feedback and translate it into natural-looking color transformations on resource-constrained user devices. We introduce FedPAIE, a federated personalized aesthetic image enhancement framework for user-adaptive color grading without centralizing raw photos or ratings. FedPAIE trains a lightweight dual-cue aesthetic scorer, calibrates it into a personalized scorer on a small local support set, and freezes it to guide regularized adaptation of a lightweight CLUT enhancer from unpaired local photographs. Fidelity constraints and an excess-gap penalty regularize scorer-guided adaptation to limit proxy-score over-optimization while preserving content and natural appearance. Training remains lightweight throughout the pipeline: scorer learning updates at most 0.787M parameters, enhancer adaptation updates 0.265M, and inference retains only a 0.293M-parameter personalized enhancer. Experiments on MIT-Adobe FiveK and Flickr-AES demonstrate effective open-world personalization and a favorable balance between user preference and image fidelity. FedPAIE thus connects decentralized preference learning with efficient personalized image transformation without requiring paired user retouches.
