FaceCrafter：身份条件扩散模型，实现面部姿态、表情与情感的分离控制
FaceCrafter: Identity-Conditional Diffusion with Disentangled Control over Facial Pose, Expression, and Emotion
AI总结：
FaceCrafter提出一种身份条件扩散模型，通过轻量级控制模块和正交化训练策略，在保持身份的同时独立控制面部姿态、表情与情感，提升控制精度和生成多样性。
摘要：
人类面部图像编码了丰富的信息谱系，既包含稳定的身份相关特征，也包含姿态、表情和情感等可变属性。尽管图像生成领域的最新进展已能实现高质量的身份条件面部合成，但对非身份属性的精确控制仍然具有挑战性，且将身份与这些可变因素解耦尤为困难。为应对这些局限，我们提出了一种新颖的身份条件扩散模型，引入两个轻量级控制模块，旨在独立操控面部姿态、表情和情感，同时不损害身份保持。这些模块嵌入基础扩散模型的交叉注意力层中，以最小的参数开销实现精确的属性控制。此外，我们定制的训练策略利用身份特征与每个非身份控制特征之间的交叉注意力，促使身份特征与控制信号保持正交，从而增强可控性和多样性。定量与定性评估以及感知用户研究表明，我们的方法在姿态、表情和情感的控制精度上超越了现有方法，同时在仅身份条件下的生成多样性方面也有所提升。
英文摘要：
Human facial images encode a rich spectrum of information, encompassing both stable identity-related traits and mutable attributes such as pose, expression, and emotion. While recent advances in image generation have enabled high-quality identity-conditional face synthesis, precise control over non-identity attributes remains challenging, and disentangling identity from these mutable factors is particularly difficult. To address these limitations, we propose a novel identity-conditional diffusion model that introduces two lightweight control modules designed to independently manipulate facial pose, expression, and emotion without compromising identity preservation. These modules are embedded within the cross-attention layers of the base diffusion model, enabling precise attribute control with minimal parameter overhead. Furthermore, our tailored training strategy, which leverages cross-attention between the identity feature and each non-identity control feature, encourages identity features to remain orthogonal to control signals, enhancing controllability and diversity. Quantitative and qualitative evaluations, along with perceptual user studies, demonstrate that our method surpasses existing approaches in terms of control accuracy over pose, expression, and emotion, while also improving generative diversity under identity-only conditioning.
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。
