实现低延迟长序列任意动作风格化，实时生成稳定流畅的动画。
LILAC: Long-sequence Incremental Low-latency Arbitrary Motion Stylization via Streaming VAE-Diffusion with Causal Decoding
- 采用潜空间流式架构与因果解码，支持在线连续生成。
- 在基准数据集上实现高质量风格化，且无未来帧依赖。
- 适合需要实时角色控制的交互式应用，如游戏与虚拟人。
在要求持续、响应迅速的角色控制的应用中，实现实时生成长序列且风格化的动作至关重要。尽管重要，现有流式方法通常直接在原始动作空间操作，导致显著计算开销，并难以保持时间稳定性。相比之下，基于潜空间的VAE-Diffusion框架虽能缓解这些问题并实现高质量风格化，但通常局限于离线处理。为弥合这一差距，LILAC（通过流式VAE-Diffusion与因果解码实现长序列增量式低延迟任意动作风格化）基于一个高性能的离线任意动作风格化框架，通过滑动窗口因果设计和注入解码动作特征，将其扩展至在线设置。该架构无需依赖未来帧，也不修改扩散模型结构，即可实现长序列实时任意风格化，实验表明其在风格化质量与响应速度之间取得了良好平衡。补充视频与示例见项目页面：https://pren1.github.io/lilac/
原文摘要 · Abstract (English)
Generating long and stylized human motions in real time is critical for applications that demand continuous and responsive character control. Despite its importance, existing streaming approaches often operate directly in the raw motion space, leading to substantial computational overhead and making it difficult to maintain temporal stability. In contrast, latent-space VAE-Diffusion-based frameworks alleviate these issues and achieve high-quality stylization, but they are generally confined to offline processing. To bridge this gap, LILAC (Long-sequence Incremental Low-latency Arbitrary Motion Stylization via Streaming VAE-Diffusion with Causal Decoding) builds upon a recent high-performing offline framework for arbitrary motion stylization and extends it to an online setting through a latent-space streaming architecture with a sliding-window causal design and the injection of decoded motion features to ensure smooth motion transitions. This architecture enables long-sequence real-time arbitrary stylization without relying on future frames or modifying the diffusion model architecture, achieving a favorable balance between stylization quality and responsiveness as demonstrated by experiments on benchmark datasets. Supplementary video and examples are available at the project page: https://pren1.github.io/lilac/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。