StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915896002347008 |
|---|---|
| author | Sun, Zhiyao Peng, Ziqiao Ma, Yifeng Chen, Yi Zhou, Zhengguang Zhou, Zixiang Zhang, Guozhen Zhang, Youliang Zhou, Yuan Lu, Qinglin Liu, Yong-Jin |
| author_facet | Sun, Zhiyao Peng, Ziqiao Ma, Yifeng Chen, Yi Zhou, Zhengguang Zhou, Zixiang Zhang, Guozhen Zhang, Youliang Zhou, Yuan Lu, Qinglin Liu, Yong-Jin |
| contents | 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 restricted to the 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: https://streamavatar.github.io . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22065 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars Sun, Zhiyao Peng, Ziqiao Ma, Yifeng Chen, Yi Zhou, Zhengguang Zhou, Zixiang Zhang, Guozhen Zhang, Youliang Zhou, Yuan Lu, Qinglin Liu, Yong-Jin Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction 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 restricted to the 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: https://streamavatar.github.io . |
| title | StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.22065 |