MultiCompose：基于每个主体属性绑定的多概念个性化生成
MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding
浏览论文内容
中文总结 AI 辅助
MultiCompose是解耦多概念个性化与多主体推理的图像生成框架，通过语义保留正则化和两阶段推理解决主体身份退化与属性错位问题，引入的MSP-Bench可联合评估相关指标，性能优于现有方法。
中文摘要 AI 辅助
文本到图像扩散模型可基于少量参考图像实现特定视觉概念的个性化生成，但生成包含多个个性化主体且每个主体绑定用户指定属性（如服饰、配饰、手持物品）的单张图像仍是未解决的问题。若无显式空间约束，同时激活的概念检查点会产生重叠的交叉注意力响应，导致每个主体的身份退化和属性错位；此外，尚无基准在个性化多主体场景中联合评估这两种失效模式。本文提出MultiCompose，一种将每个概念的个性化与多主体推理解耦的生成框架：语义保留正则化在微调期间维持属性绑定能力，而两阶段推理过程通过空间互斥掩码自动建立主体布局并合成每个概念的预测结果。我们进一步引入MSP-Bench，一种通过双路径协议联合评估身份保真度（ID）、属性绑定准确率（BIND）和属性错位（MIS）的基准。实验表明，MultiCompose在常规指标和MSP-Bench上均优于现有方法，证实该基准能够揭示常规指标忽略的失效模式。代码可在指定URL获取。
英文摘要
Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single image that contains multiple personalized subjects, each bound to user-specified attributes such as clothing, accessories, and held objects, remains largely unaddressed. Without explicit spatial constraints, concurrently activated concept checkpoints produce overlapping cross-attention responses, causing per-subject identity degradation and attribute misalignment. Moreover, no established benchmark jointly evaluates these two failure modes in the personalized multi-subject setting. We present MultiCompose, a composition framework that decouples per-concept personalization from multi-subject inference. A semantic preservation regularization maintains attribute binding capacity during fine-tuning, while a two-phase inference procedure automatically establishes subject layout and composes per-concept predictions through spatially exclusive masks. We further introduce MSP-Bench, a benchmark that jointly evaluates identity fidelity (ID), attribute binding accuracy (BIND), and attribute misalignment (MIS) through a dual-pathway protocol. Experiments show that MultiCompose outperforms existing methods on both conventional metrics and MSP-Bench, confirming the benchmark's ability to reveal failure modes that conventional metrics overlook. Code is available at https://github.com/I2-Multimedia-Lab/MultiCompose
