ExpPortrait：通过个性化表征生成富有表现力的肖像
ExpPortrait: Expressive Portrait Generation via Personalized Representation
用高保真个性化头部表征（静态身份几何+动态表情细节）替代 2D landmark/参数化模型作为条件信号，驱动 DiT 生成肖像视频；做肖像动画或可控视频生成时，这套解耦表征与表情迁移模块可直接作为条件编码方案复用。
原文依据 we propose a high-fidelity personalized head representation that more effectively disentangles expression and identity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论尽管扩散模型在肖像生成中展现出巨大潜力，但生成富有表现力、连贯且可控的电影级肖像视频仍是一项重大挑战。现有的肖像生成中间信号，如 2D 关键点和参数化模型，由于其为稀疏或低秩表征，解耦能力有限，无法表达个性化细节。因此，基于这些模型的现有方法难以准确保持主体身份和表情，阻碍了高表现力肖像视频的生成。为克服这些局限，我们提出了一种高保真个性化头部表征，能更有效地解耦表情与身份。该表征同时捕捉静态的、主体特定的全局几何结构与动态的、与表情相关的细节。此外，我们引入了一个表情迁移模块，以实现不同身份之间头部姿态和表情细节的个性化迁移。我们将这一精细且极具表现力的头部模型作为条件信号，训练基于扩散 Transformer（DiT）的生成器以合成细节丰富的肖像视频。在自重建与跨重建任务上的大量实验表明，我们的方法在身份保持、表情准确性和时序稳定性方面优于先前模型，尤其在捕捉复杂运动的细粒度细节方面表现突出。
英文原文摘要 1458 字符
While diffusion models have shown great potential in portrait generation, generating expressive, coherent, and controllable cinematic portrait videos remains a significant challenge. Existing intermediate signals for portrait generation, such as 2D landmarks and parametric models, have limited disentanglement capabilities and cannot express personalized details due to their sparse or low-rank representation. Therefore, existing methods based on these models struggle to accurately preserve subject identity and expressions, hindering the generation of highly expressive portrait videos. To overcome these limitations, we propose a high-fidelity personalized head representation that more effectively disentangles expression and identity. This representation captures both static, subject-specific global geometry and dynamic, expression-related details. Furthermore, we introduce an expression transfer module to achieve personalized transfer of head pose and expression details between different identities. We use this sophisticated and highly expressive head model as a conditional signal to train a diffusion transformer (DiT)-based generator to synthesize richly detailed portrait videos. Extensive experiments on self- and cross-reenactment tasks demonstrate that our method outperforms previous models in terms of identity preservation, expression accuracy, and temporal stability, particularly in capturing fine-grained details of complex motion.