X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915426863153152 |
|---|---|
| author | Zhang, Chenxu Li, Zenan Xu, Hongyi Xie, You Zhao, Xiaochen Gu, Tianpei Song, Guoxian Chen, Xin Liang, Chao Jiang, Jianwen Luo, Linjie |
| author_facet | Zhang, Chenxu Li, Zenan Xu, Hongyi Xie, You Zhao, Xiaochen Gu, Tianpei Song, Guoxian Chen, Xin Liang, Chao Jiang, Jianwen Luo, Linjie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02944 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio Zhang, Chenxu Li, Zenan Xu, Hongyi Xie, You Zhao, Xiaochen Gu, Tianpei Song, Guoxian Chen, Xin Liang, Chao Jiang, Jianwen Luo, Linjie Computer Vision and Pattern Recognition 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. |
| title | X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.02944 |