PositionIC：面向图像定制的统一位置与身份一致性
PositionIC: Unified Position and Identity Consistency for Image Customization
用 NeRF 式体素权重调节的可见性感知注意力，把实例级空间嵌入与语义身份特征解耦，可直接迁移到任何需要精确布局控制的多主体生成/编辑框架中；BMPDS 自动数据合成管线也为位置标注数据稀缺问题提供了可复用方案。
原文依据 a novel visibility-aware attention mechanism
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的主体驱动图像定制在保真度方面表现出色，但细粒度的实例级空间控制仍是一项难以实现的挑战，阻碍了其在实际场景中的应用。这一局限源于两个因素：可扩展的位置标注数据集稀缺，以及全局注意力机制对身份与布局的纠缠。为此，我们提出 PositionIC，一个用于高保真、空间可控的多主体定制的统一框架。首先，我们提出 BMPDS，这是首个面向位置标注多主体数据集的自动数据合成管线，有效提供了关键的空间监督。其次，我们设计了一个轻量级、布局感知的扩散框架，集成了新颖的可见性感知注意力机制。该机制通过受 NeRF 启发的体素权重调节来显式建模空间关系，从而有效将实例级空间嵌入与语义身份特征解耦，实现多个主体精确且遮挡感知的放置。大量实验表明，PositionIC 在公开基准上达到最优性能，在空间精度与身份一致性方面创下新纪录。我们的工作朝着多实体场景下真正可控、高保真的图像定制迈出了重要一步。代码与数据：https://github.com/MeiGen-AI/PositionIC。
英文原文摘要 1385 字符
Recent subject-driven image customization excels in fidelity, yet fine-grained instance-level spatial control remains an elusive challenge, hindering real-world applications. This limitation stems from two factors: a scarcity of scalable, position-annotated datasets, and the entanglement of identity and layout by global attention mechanisms. To this end, we introduce PositionIC, a unified framework for high-fidelity, spatially controllable multi-subject customization. First, we present BMPDS, the first automatic data-synthesis pipeline for position-annotated multi-subject datasets, effectively providing crucial spatial supervision. Second, we design a lightweight, layout-aware diffusion framework that integrates a novel visibility-aware attention mechanism. This mechanism explicitly models spatial relationships via an NeRF-inspired volumetric weight regulation to effectively decouple instance-level spatial embeddings from semantic identity features, enabling precise, occlusion-aware placement of multiple subjects. Extensive experiments demonstrate PositionIC achieves state-of-the-art performance on public benchmarks, setting new records for spatial precision and identity consistency. Our work represents a significant step towards truly controllable, high-fidelity image customization in multi-entity scenarios.Code and data: https://github.com/MeiGen-AI/PositionIC.