用掩码扩散模型生成3D动作，支持关键帧控制且泛化能力强。
Towards Robust and Controllable Text-to-Motion via Masked Autoregressive Diffusion
- 融合掩码建模与扩散过程，用连续帧表示生成动作
- 在稀疏关键帧提示下仍能准确还原新动作，优于现有方法
- 适合需要精准时空控制的虚拟角色动画场景
从文本生成3D人体动作仍具挑战性，因人类动作多样且复杂。现有方法在训练分布内表现良好，但在分布外动作上性能下降，限制实际应用。基于VQVAE的方法难以用离散编码忠实表达新动作，而基于扩散的连续表示方法常缺乏对单帧的精细控制。为此，我们提出MoMADiff框架，结合掩码建模与扩散过程，采用帧级连续表示生成动作。模型支持用户灵活指定关键帧，实现对动作空间与时间维度的精确控制。在两个留出数据集和两个标准基准上的实验表明，该方法在动作质量、指令忠实度和关键帧遵循性方面持续优于当前最先进模型。代码已开源。
原文摘要 · Abstract (English)
Generating 3D human motion from text descriptions remains challenging due to the diverse and complex nature of human motion. While existing methods excel within the training distribution, they often struggle with out-of-distribution motions, limiting their applicability in real-world scenarios. Existing VQVAE-based methods often fail to represent novel motions faithfully using discrete tokens, which hampers their ability to generalize beyond seen data. Meanwhile, diffusion-based methods operating on continuous representations often lack fine-grained control over individual frames. To address these challenges, we propose a robust motion generation framework MoMADiff, which combines masked modeling with diffusion processes to generate motion using frame-level continuous representations. Our model supports flexible user-provided keyframe specification, enabling precise control over both spatial and temporal aspects of motion synthesis. MoMADiff demonstrates strong generalization capability on novel text-to-motion datasets with sparse keyframes as motion prompts. Extensive experiments on two held-out datasets and two standard benchmarks show that our method consistently outperforms state-of-the-art models in motion quality, instruction fidelity, and keyframe adherence. The code is available at: https://github.com/zzysteve/MoMADiff
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。