T2M Mamba：基于运动周期性与显著性耦合的稳定文本驱动运动生成方法
T2M Mamba: Motion Periodicity-Saliency Coupling Approach for Stable Text-Driven Motion Generation
AI总结：
T2M Mamba通过周期性-显著性耦合方法，解决文本驱动运动生成中的周期性漂移和语义脆弱性问题，实现更稳定的运动生成。
摘要：
文本到运动生成，即把运动语言描述转换为连贯的3D人体运动序列，已在avatar动画和人形机器人交互等领域受到越来越多关注。尽管现有模型已取得显著保真度，但仍存在两个核心限制：(i) 它们将运动周期性和关键帧显著性视为独立因素，忽视了它们的耦合关系，导致长序列生成漂移。(ii) 它们对语义等价的改写很脆弱，其中微小的同义词替换会扭曲文本嵌入，通过解码器传播，产生不稳定或错误的运动。在本文中，我们提出T2M Mamba来解决这些限制：(i) 提出周期性-显著性感知Mamba，利用改进的密度峰聚类和FFT加速的自相关算法，通过新颖的算法估计关键帧权重和运动周期性，以最小的计算开销捕捉耦合动态；(ii) 构建周期性微分跨模态对齐模块（PDCAM），以增强文本和运动嵌入的鲁棒对齐。在HumanML3D和KIT-ML数据集上进行了大量实验，证实了我们方法的有效性，实现了FID为0.068，并在所有其他指标上实现了稳定提升。
英文摘要：
Text-to-motion generation, which converts motion language descriptions into coherent 3D human motion sequences, has attracted increasing attention in fields, such as avatar animation and humanoid robotic interaction. Though existing models have achieved significant fidelity, they still suffer from two core limitations: (i) They treat motion periodicity and keyframe saliency as independent factors, overlooking their coupling and causing generation drift in long sequences. (ii) They are fragile to semantically equivalent paraphrases, where minor synonym substitutions distort textual embeddings, propagating through the decoder and producing unstable or erroneous motions. In this work, we propose T2M Mamba to address these limitations by (i) proposing Periodicity-Saliency Aware Mamba, which utilizes novel algorithms for keyframe weight estimation via enhanced Density Peaks Clustering and motion periodicity estimation via FFT-accelerated autocorrelation to capture coupled dynamics with minimal computational overhead, and (ii) constructing a Periodic Differential Cross-modal Alignment Module (PDCAM) to enhance robust alignment of textual and motion embeddings. Extensive experiments on HumanML3D and KIT-ML datasets have been conducted, confirming the effectiveness of our approach, achieving an FID of 0.068 and consistent gains on all other metrics.
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。
