Abstract
Real-time, streaming interactive avatars represent a critical yet challenging goal in digital human research. Although diffusion-based human avatar generation methods achieve remarkable success, their non-causal architecture and high computational costs make them unsuitable for streaming. Moreover, existing interactive approaches are typically limited to head-and-shoulder region, limiting their ability to produce gestures and body motions. To address these challenges, we propose a two-stage autoregressive adaptation and acceleration framework that applies autoregressive distillation and adversarial refinement to adapt a high-fidelity human video diffusion model for real-time, interactive streaming. To ensure long-term stability and consistency, we introduce three key components: a Reference Sink, a Reference-Anchored Positional Re-encoding (RAPR) strategy, and a Consistency-Aware Discriminator. Building on this framework, we develop a one-shot, interactive, human avatar model capable of generating both natural talking and listening behaviors with coherent gestures. Extensive experiments demonstrate that our method achieves state-of-the-art performance, surpassing existing approaches in generation quality, real-time efficiency, and interaction naturalness. Project page: this https URL .
Abstract (translated)
实时流媒体互动化身代表了数字人类研究中的一个关键但具有挑战性的目标。尽管基于扩散的人类化身生成方法取得了显著的成功，但由于其非因果架构和高昂的计算成本，这些方法不适合用于流媒体应用。此外，现有的交互式方法通常局限于头部和肩部区域，限制了它们生成手势和身体动作的能力。 为了解决这些挑战，我们提出了一种两阶段自回归适应和加速框架，该框架通过自回归蒸馏和对抗性优化来调整高保真的人类视频扩散模型，使其适用于实时交互流媒体。为了确保长期稳定性和一致性，我们引入了三个关键组件：参考源（Reference Sink）、基于参考的位置重编码策略（RAPR）以及一种感知一致性的判别器。 在此框架的基础上，我们开发了一种一次性、互动式的人类化身模型，能够生成自然的说话和倾听行为，并且具备连贯的手势。广泛的实验表明，我们的方法在生成质量、实时效率及交互自然度方面均达到了业界领先水平，超过了现有的方法。项目页面：[请参见原文链接]。 请注意，最后一个句子中的“[请参见原文链接]”需要您查看原始文档以获取实际的链接地址。
URL
https://arxiv.org/abs/2512.22065
