Pose-ICL：面向姿态可控主体定制的3D感知上下文学习
Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization
AI总结：
提出Pose-ICL框架，通过3D感知上下文学习和表面锚定位置嵌入（SAPE）实现无调优的姿态可控主体定制，显著提升姿态准确性和身份一致性。
摘要：
主体定制是现代图像生成中的基础任务。通过提供少量参考图像和文本提示，用户可以生成特定对象在任意期望场景中的图像。然而，现有方法在实现定制主体的有效姿态控制方面仍存在困难。在实践中，它们常常表现出不准确的姿态或不一致的跨姿态外观。这些局限性表明，对于2D原生骨干网络而言，以体积方式理解对象仍然是一个重大挑战。为了应对这一挑战，我们提出了Pose-ICL，这是一个无需调优的框架，利用3D感知上下文学习（ICL）通过多个配对的图像-姿态参考直接适应新主体。其核心机制——表面锚定位置嵌入（SAPE）——通过将图像令牌锚定到体积边界框的表面坐标，赋予模型显式的3D感知能力。专门的优化确保了其与现有DiT模型的无缝兼容性。在3D资产和真实世界主体上的广泛评估表明，Pose-ICL在姿态准确性和身份一致性方面均显著优于当前方法。
英文摘要：
Subject Customization is a foundational task in modern image generation. By providing a few reference images and a text prompt, users can generate images of a specific object in any desired scene. However, existing methods still struggle to achieve effective pose control for customized subjects. In practice, they often exhibit inaccurate poses or inconsistent cross-pose appearances. These limitations suggest that understanding objects in a volumetric manner remains a significant challenge for 2D-native backbones. To address this challenge, we propose Pose-ICL, a tuning-free framework that leverages 3D-aware In-Context Learning (ICL) to directly adapt to new subjects through multiple paired image-pose references. Its core mechanism,Surface-Anchored Position Embedding (SAPE), equips the model with explicit 3D awareness by anchoring image tokens to the surface coordinates of a volumetric bounding box. Dedicated refinements ensure its seamless compatibility with existing DiT models. Extensive evaluations on both 3D assets and real-world subjects demonstrate that Pose-ICL significantly outperforms current methods in both pose accuracy and identity consistency.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
