PALATE：面向多用户人像修图的基于自适应品味演化的个性化美学学习
PALATE: Personalized Aesthetic Learning through Adaptive Taste Evolution for Multi-User Portrait Retouching
浏览论文内容
中文总结 AI 辅助
针对多用户人像修图的个体品味差异问题，提出PALATE框架，通过共享奖励演化结合双层级蒸馏实现个性化修图，在PPR10K数据集上准确率达72.83%，优于现有基线且用户成本极低。
中文摘要 AI 辅助
自动人像修图技术已取得快速进展，但其目标本质上具有主观性：同一人像可存在多种专业层面有效的修图结果，且用户对最佳结果的偏好存在差异。现有多数方法针对群体层面的美学标准进行优化，无法捕捉个体品味，而为每个用户微调单独的编辑模型则会产生过高的训练、存储及数据成本。本文提出PALATE，这是一种共享奖励演化框架，其保持图像编辑器固定，仅在同一源人像的修图候选结果中进行个性化选择。PALATE将每个用户的奖励分解为三个部分：所有用户共享的全局主干、美学相似用户共享的类别级残差，以及轻量型用户适配器，同时采用抗崩溃正则化器确保三个层级互补。循环双层级蒸馏方案先将用户特定偏好蒸馏为类别奖励，再将所得类别级知识整合至全局主干，该主干会被重新分配以初始化下一轮演化。通过这种方式，共享初始化会在各轮中逐步改进，使未见过的用户仅需少量排序即可完成校准。在PPR10K数据集的专家修图候选结果上，针对保留的用户和保留的图像，PALATE的成对偏好预测准确率达到72.83%，优于所有奖励、美学及图像质量基线，其中最强基线PickScore的准确率为58.06%。每个新用户仅需512字节的用户特定参数及毫秒级评分时间。
英文摘要
Automatic portrait retouching has advanced rapidly, yet its objective is inherently subjective: the same portrait admits multiple professionally valid results, and users disagree about which one is best. Most existing methods optimize a population-level aesthetic standard and therefore cannot capture individual taste, while fine-tuning a separate editing model for every user incurs prohibitive training, storage, and data costs. We propose PALATE, a shared reward-evolution framework that keeps the image editor fixed and instead personalizes the selection among retouched candidates of the same source portrait. PALATE decomposes the reward for each user into a global backbone shared by all users, category-level residuals shared by aesthetically similar users, and a lightweight user adapter, with anti-collapse regularizers keeping the three levels complementary.A cyclic dual-level distillation scheme first distills user-specific preferences into category rewards and then consolidates the resulting category-level knowledge into the global backbone, which is redistributed to initialize the next evolution round. In this way, the shared initialization improves progressively across rounds, enabling unseen users to be calibrated from only a few rankings. On expert-retouched candidates from PPR10K with held-out users and held-out images, PALATE attains 72.83% pairwise preference-prediction accuracy, surpassing all reward, aesthetic, and image-quality baselines, of which the strongest, PickScore, reaches 58.06%. Each new user costs only 512 bytes of user-specific parameters and millisecond-level scoring.
