像鸡一样跳舞：面向人体运动扩散模型的低秩风格化
Dance Like a Chicken: Low-Rank Stylization for Human Motion Diffusion
AI总结：
本文提出LoRA-MDM，通过低秩适配少量风格样本调整运动扩散先验，在保持分布结构和可编辑性的同时实现逼真风格注入，并支持风格混合与运动编辑。
摘要：
文本到运动生成模型能够覆盖广泛的3D人体动作，但在诸如“鸡”风格等细腻的风格属性方面仍存在困难。由于风格特定数据的稀缺，现有方法将生成先验拉向参考风格，这往往导致分布外（out-of-distribution）的低质量生成。在本工作中，我们提出了LoRA-MDM，这是一个轻量级的运动风格化框架，能够泛化到复杂动作，同时保持可编辑性。我们的核心见解是：在保持整体分布的同时调整生成先验以包含风格，比在生成过程中修改每个单独的运动更有效。基于这一思想，LoRA-MDM仅使用少量样本即可学习调整先验以纳入参考风格。随后，该风格可用于不同文本提示下的生成。低秩适配以语义上有意义的方式移动运动流形，即使对于参考样本中未出现的动作，也能实现逼真的风格注入。此外，保留分布结构还支持风格混合和运动编辑等高级操作。我们将LoRA-MDM与最先进的风格化运动生成方法进行比较，展示了文本保真度与风格一致性之间的良好平衡。
英文摘要：
Text-to-motion generative models span a wide range of 3D human actions but struggle with nuanced stylistic attributes such as a "Chicken" style. Due to the scarcity of style-specific data, existing approaches pull the generative prior towards a reference style, which often results in out-of-distribution low quality generations. In this work, we introduce LoRA-MDM, a lightweight framework for motion stylization that generalizes to complex actions while maintaining editability. Our key insight is that adapting the generative prior to include the style, while preserving its overall distribution, is more effective than modifying each individual motion during generation. Building on this idea, LoRA-MDM learns to adapt the prior to include the reference style using only a few samples. The style can then be used in the context of different textual prompts for generation. The low-rank adaptation shifts the motion manifold in a semantically meaningful way, enabling realistic style infusion even for actions not present in the reference samples. Moreover, preserving the distribution structure enables advanced operations such as style blending and motion editing. We compare LoRA-MDM to state-of-the-art stylized motion generation methods and demonstrate a favorable balance between text fidelity and style consistency.
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。
