PortraitDirector：面向可控实时人脸重演的分层解耦框架
PortraitDirector: A Hierarchical Disentanglement Framework for Controllable and Real-time Facial Reenactment
把面部运动拆成空间层（头姿+局部表情）与语义层（情绪）再重组为运动潜码，配合扩散蒸馏与因果注意力实现 20FPS 流式人脸重演，为可控人脸编辑提供了可复用的分层解耦与实时化方案。
原文依据 deconstructing facial motion into a Spatial Layer for physical movements and a Semantic Layer for emotional content
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现有的人脸重演方法难以在表现力与细粒度可控性之间取得平衡。整体式人脸重演模型往往为表现力牺牲细粒度控制，而为控制而设计的方法又可能在保真度与稳健解耦上表现不佳。本文不再将面部运动视为单一整体信号，而是探索一种组合式视角。我们提出 PortraitDirector，一个将人脸重演建模为分层组合任务的新框架，可实现高保真且可控的结果。我们采用分层运动解耦与组合策略，将面部运动分解为负责物理运动的空间层与负责情绪内容的语义层。空间层包括：(i) 全局头部姿态，通过专门的表示与注入通路进行管理；(ii) 空间上分离的局部面部表情，从裁剪的面部区域中提取，并借助基于信息瓶颈的情绪过滤模块去除情绪线索。语义层包含推导得到的全局情绪。解耦后的各分量随后被重组为富有表现力的运动潜码。此外，我们通过扩散蒸馏、因果注意力与变分自编码器加速等一系列优化，使框架具备实时性能。PortraitDirector 在单块 5090 GPU 上实现了 512 x 512 的流式、高保真、可控人脸重演，达到 20 FPS，端到端延迟为 800 ms。
英文原文摘要 1544 字符
Existing facial reenactment methods struggle with a trade-off between expressiveness and fine-grained controllability. Holistic facial reenactment models often sacrifice granular control for expressiveness, while methods designed for control may struggle with fidelity and robust disentanglement. Instead of treating facial motion as a monolithic signal, we explore an alternative compositional perspective. In this paper, we introduce PortraitDirector, a novel framework that formulates face reenactment as a hierarchical composition task, achieving high-fidelity and controllable results. We employ a Hierarchical Motion Disentanglement and Composition strategy, deconstructing facial motion into a Spatial Layer for physical movements and a Semantic Layer for emotional content. The Spatial Layer comprises: (i) global head pose, managed via a dedicated representation and injection pathway; (ii) spatially separated local facial expressions, distilled from cropped facial regions and purged of emotional cues via Emotion-Filtering Module leveraging an information bottleneck. The Semantic Layer contains a derived global emotion. The disentangled components are then recomposed into an expressive motion latent. Furthermore, we engineer the framework for real-time performance through a suite of optimizations, including diffusion distillation, causal attention and VAE acceleration. PortraitDirector achieves streaming, high-fidelity, controllable 512 x 512 face reenactment at 20 FPS with a end-to-end 800 ms latency on a single 5090 GPU.