面向姿态不变身份保持扩散的语义对齐
Semantic Alignment for Pose-Invariant Identity Preserving Diffusion
免训练的身份保持生成框架，通过语义匹配注入参考外观并用 guidance delta 调和文本-外观冲突，可直接用于姿态变化下的人物/动物个性化生成，避免对主体进行『再想象』。
原文依据 a novel training-free framework that addresses the 're-imagining' problem from the perspective of 'infusion'
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文本到图像扩散模型已发展到可控制多种条件，包括结构、外观和提示词。尽管取得了这些进展，基于训练的方法需要大量计算，而免训练方法往往会对主体进行『再想象』以满足给定结构，从而损害身份保持并削弱精细纹理。我们提出 SeAl（面向姿态不变身份保持扩散的语义对齐），这是一个新颖的免训练框架，从『注入』的视角解决『再想象』问题。SeAl 通过三个模块将结构、外观和提示词整合起来：AnchorAlign 预对齐空间差异，Reference-guided Appearance Infusion 通过语义匹配注入身份，Delta-Bridge 利用引导增量来调和文本与外观之间的冲突。我们证明，我们的方法忠实反映了全部三个控制因素，并大幅减少了先前方法中普遍存在的身份泄漏。值得注意的是，SeAl 在身份保持通常失败的挑战性数据集上（例如具有独特特征的动物或复杂的人类服饰）表现出色，为扩散模型中的免训练身份保持建立了一种新范式。
英文原文摘要 1225 字符
Recent T2I diffusion models have evolved to control multiple conditions, including structure, appearance, and text prompt. Despite this progress, training-based methods demand heavy computation, whereas training-free methods often 're-imagine' the subject to satisfy given structure, thereby compromising identity preservation and attenuating fine textures.We propose SeAl (Semantic Alignment for Pose-Invariant Identity Preserving Diffusion), a novel training-free framework that addresses the 're-imagining' problem from the perspective of 'infusion'. SeAl integrates structure, appearance, and text prompt with three modules: AnchorAlign pre-aligns spatial discrepancies, Reference-guided Appearance Infusion injects identity via semantic matching, and Delta-Bridge leverages the guidance delta to mediate text-appearance conflicts. We demonstrate that our method faithfully reflects all three control factors and dramatically reduces the identity leakage endemic to prior methods. Notably, SeAl excels on challenging datasets where identity preservation typically fails (e.g., distinctive animal features or complex human attire), establishing a novel paradigm for training-free identity preservation in diffusion models.