因果运动扩散模型用于自回归运动生成
Causal Motion Diffusion Models for Autoregressive Motion Generation
AI总结：
本文提出因果运动扩散模型，通过因果扩散变换器实现高质量运动生成，提升语义保真度与时间平滑度，同时减少推理延迟。
摘要：
最近在运动扩散模型方面的进展大幅提升了人类运动合成的逼真度。然而，现有方法要么依赖于全序列扩散模型进行双向生成，这限制了时间因果性和实时应用性，要么使用自回归模型，这些模型会受到不稳定性和累积误差的影响。在本工作中，我们提出了因果运动扩散模型（CMDM），这是一种基于因果扩散变换器的统一框架，用于自回归运动生成，该变换器在语义对齐的潜在空间中运行。CMDM建立在运动-语言对齐的因果变分自编码器（MAC-VAE）之上，将运动序列编码为时间因果的潜在表示。在此潜在表示之上，使用因果扩散强制训练自回归扩散变换器，以在运动帧之间执行时间有序的去噪。为了实现快速推理，我们引入了带有因果不确定性的帧级采样计划，其中每个后续帧都从部分去噪的先前帧中预测。所得到的框架支持高质量的文本到运动生成、流式合成和长视界运动生成，以交互速率进行。在HumanML3D和SnapMoGen上的实验表明，CMDM在语义保真度和时间平滑度方面均优于现有的扩散和自回归模型，同时显著减少了推理延迟。
英文摘要：
Recent advances in motion diffusion models have substantially improved the realism of human motion synthesis. However, existing approaches either rely on full-sequence diffusion models with bidirectional generation, which limits temporal causality and real-time applicability, or autoregressive models that suffer from instability and cumulative errors. In this work, we present Causal Motion Diffusion Models (CMDM), a unified framework for autoregressive motion generation based on a causal diffusion transformer that operates in a semantically aligned latent space. CMDM builds upon a Motion-Language-Aligned Causal VAE (MAC-VAE), which encodes motion sequences into temporally causal latent representations. On top of this latent representation, an autoregressive diffusion transformer is trained using causal diffusion forcing to perform temporally ordered denoising across motion frames. To achieve fast inference, we introduce a frame-wise sampling schedule with causal uncertainty, where each subsequent frame is predicted from partially denoised previous frames. The resulting framework supports high-quality text-to-motion generation, streaming synthesis, and long-horizon motion generation at interactive rates. Experiments on HumanML3D and SnapMoGen demonstrate that CMDM outperforms existing diffusion and autoregressive models in both semantic fidelity and temporal smoothness, while substantially reducing inference latency.
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。
