X-Actor：基于音频的情感化与表现力长距离肖像表演
X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio
AI总结：
X-Actor提出两阶段解耦生成流水线，利用自回归扩散模型预测面部运动潜在标记，实现从音频和单图生成情感丰富、长距离电影级肖像表演，达到最先进水平。
摘要：
我们提出了X-Actor，一种新颖的音频驱动肖像动画框架，能够从单张参考图像和一段输入音频片段生成逼真、情感丰富的说话头视频。与以往强调在受限说话场景中唇形同步和短距离视觉保真度的方法不同，X-Actor实现了演员级质量的长形式肖像表演，捕捉与语音节奏和内容连贯流动的细微、动态演变的情感。我们方法的核心是一个两阶段解耦生成流水线：一个音频条件自回归扩散模型，在长时间上下文窗口内预测富有表现力且与身份无关的面部运动潜在标记；随后是一个基于扩散的视频合成模块，将这些运动转化为高保真视频动画。通过在与视觉和身份线索解耦的紧凑面部运动潜在空间中操作，我们的自回归扩散模型通过扩散强制训练范式有效捕捉音频与面部动态之间的长距离相关性，实现无误差累积的无限长度情感丰富运动预测。大量实验表明，X-Actor产生了引人入胜的电影风格表演，超越了标准说话头动画，并在长距离、音频驱动的情感肖像表演中达到了最先进的结果。
英文摘要：
We present X-Actor, a novel audio-driven portrait animation framework that generates lifelike, emotionally expressive talking head videos from a single reference image and an input audio clip. Unlike prior methods that emphasize lip synchronization and short-range visual fidelity in constrained speaking scenarios, X-Actor enables actor-quality, long-form portrait performance capturing nuanced, dynamically evolving emotions that flow coherently with the rhythm and content of speech. Central to our approach is a two-stage decoupled generation pipeline: an audio-conditioned autoregressive diffusion model that predicts expressive yet identity-agnostic facial motion latent tokens within a long temporal context window, followed by a diffusion-based video synthesis module that translates these motions into high-fidelity video animations. By operating in a compact facial motion latent space decoupled from visual and identity cues, our autoregressive diffusion model effectively captures long-range correlations between audio and facial dynamics through a diffusion-forcing training paradigm, enabling infinite-length emotionally-rich motion prediction without error accumulation. Extensive experiments demonstrate that X-Actor produces compelling, cinematic-style performances that go beyond standard talking head animations and achieves state-of-the-art results in long-range, audio-driven emotional portrait acting.
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。
