ExpPortrait：通过个性化表示生成表现力强的肖像
ExpPortrait: Expressive Portrait Generation via Personalized Representation
AI总结：
本文提出一种高保真个性化头部表示，用于生成具有高表现力的肖像视频，通过引入表达转移模块实现不同身份间的头部姿态和表情细节转移，实验表明在身份保持、表情准确性和时间稳定性方面优于现有方法。
摘要：
尽管扩散模型在肖像生成中展现出巨大潜力，但生成具有表现力、连贯性和可控性的电影级肖像视频仍是一个重大挑战。现有肖像生成的中间信号，如2D地标和参数模型，具有有限的解耦能力，无法表达个性化细节，因为它们的稀疏或低秩表示。因此，基于这些模型的方法难以准确保留主体身份和表情，阻碍了高表现力肖像视频的生成。为克服这些限制，我们提出了一种高保真的个性化头部表示，更有效地解耦表情和身份。该表示捕捉了静态的、主体特定的全局几何和动态的、与表情相关的细节。此外，我们引入了一个表达转移模块，以实现不同身份之间的头部姿态和表情细节的个性化转移。我们使用这种复杂且高度表现力的头部模型作为条件信号，训练基于扩散变换器（DiT）的生成器来合成细节丰富的肖像视频。在自拍和跨拍摄任务上的大量实验表明，我们的方法在身份保持、表情准确性和时间稳定性方面优于先前模型，特别是在捕捉复杂运动的细粒度细节方面。
英文摘要：
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.
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。
