提出首个可控的掩码动作生成方法，实现高精度与高质量动作合成的统一。
MaskControl: Spatio-Temporal Control for Masked Motion Synthesis
- 通过逻辑正则化与优化，实现训练与推理时的动作精确控制。
- 动作质量提升（FID降低约77%），控制误差降至0.91（对比1.08）。
- 支持任意关节任意帧、身体部位时间线等多样化控制场景。
近期动作扩散模型已实现空间可控的文本到动作生成，但难以同时保证高精度控制与高质量生成。为此，我们提出MaskControl，首个为生成式掩码动作模型引入可控性的方法。该方法包含两项关键创新：一是训练时使用逻辑正则化，隐式扰动逻辑值以对齐动作标记分布与受控关节点位置，同时正则化分类标记预测以保障生成保真度；二是推理时采用逻辑优化，显式调整预测逻辑值，直接重塑标记分布，强制生成动作精准对齐受控关节点。此外，引入可微期望采样（DES）解决逻辑正则化与优化中非可微分布采样的问题。大量实验表明，MaskControl优于现有最优方法，在动作质量（FID下降约77%）和控制精度（平均误差0.91，对比1.08）上均有显著提升。同时，该方法支持任意关节任意帧控制、身体部位时间线控制及零样本目标控制等多样应用。视频演示见https://www.ekkasit.com/ControlMM-page/
原文摘要 · Abstract (English)
Recent advances in motion diffusion models have enabled spatially controllable text-to-motion generation. However, these models struggle to achieve high-precision control while maintaining high-quality motion generation. To address these challenges, we propose MaskControl, the first approach to introduce controllability to the generative masked motion model. Our approach introduces two key innovations. First, \textit{Logits Regularizer} implicitly perturbs logits at training time to align the distribution of motion tokens with the controlled joint positions, while regularizing the categorical token prediction to ensure high-fidelity generation. Second, \textit{Logit Optimization} explicitly optimizes the predicted logits during inference time, directly reshaping the token distribution that forces the generated motion to accurately align with the controlled joint positions. Moreover, we introduce \textit{Differentiable Expectation Sampling (DES)} to combat the non-differential distribution sampling process encountered by logits regularizer and optimization. Extensive experiments demonstrate that MaskControl outperforms state-of-the-art methods, achieving superior motion quality (FID decreases by ~77\%) and higher control precision (average error 0.91 vs. 1.08). Additionally, MaskControl enables diverse applications, including any-joint-any-frame control, body-part timeline control, and zero-shot objective control. Video visualization can be found at https://www.ekkasit.com/ControlMM-page/
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。