摘要：音频驱动的面部动画是实时虚拟形象、远程临场和具身虚拟 Agent 的基础。它必须能够在线运行：以交互式速率，仅根据截至当前时刻已观测到的音频输出每一帧。近期进展主要由扩散模型主导，但这类模型每生成一个样本需要进行多次网络评估，因此不适合流式场景。我们认为，在这一领域中，这种计算成本并无必要。音频条件下的面部运动处于一个相对低维的流形中，在这一设定下，单次前向的 GAN 已经足够。障碍不在于模型容量，而在于随机结构。我们证明，由独立同分布噪声驱动的因果、时不变生成器，无法在不导致其逐步创新性坍塌的情况下抑制某一频段内的输出频谱。我们提出 FaceGAN，通过以非因果方式整形噪声路径来消除这一限制。由于驱动噪声是合成的，其未来值可以在当前时刻采样，因此音频到表情的路径仍保持因果，模型也支持完全因果的运行方式。FaceGAN 每帧只需一次前向传播即可输出表情和头部姿态，并且在生成质量上达到或超过当前最先进方法。作为具有有界注意力窗口的前馈模型，它能够无限期生成而不发生漂移。

Abstract:Audio-driven facial animation underpins real-time avatars, telepresence, and embodied virtual agents. And it must run online: each frame emitted from audio observed up to the current time, at interactive rates. Recent progress is dominated by diffusion models, which need many network evaluations per sample and are therefore a poor fit for streaming. We argue the cost is unnecessary in this domain. Audio-conditioned facial motion occupies a comparatively low-dimensional manifold, a regime where a single-pass GAN suffices. The obstacle is not capacity but stochastic structure. We show that a causal, time-invariant generator driven by i.i.d. noise cannot suppress its output spectrum over a band without collapsing its per-step innovation. We proposed FaceGAN, which dissolved the limitation by shaping the noise pathway acausally. Because the driving noise is synthetic, its future can be sampled now, so the audio-to-expression path stays causal, and the model supports fully causal operation. FaceGAN emits expression and head pose in a single forward pass per frame and matches or outperforms state-of-art approaches in generation quality. Being feed-forward with bounded attention windows, it generates indefinitely without drift.