用小波流形学习预测人体运动，提升复杂动作的建模精度。
MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
- 通过小波变换将运动数据映射到时空频域，构建小波流形编码复杂动态
- 在小波潜空间上训练扩散模型，生成更符合真实运动模式的未来轨迹
- 引入空间结构引导和时序注意力机制，显著提升预测准确性和泛化能力
捕捉人体运动的时间特性与非平稳动态对预测未来动作至关重要，但复杂动作中细微的过渡变化使得建模极具挑战。本文提出MotionWavelet，一种基于小波流形学习的人体运动预测框架。该框架利用小波变换将运动数据转换至时空频域，构建小波流形以编码复杂的时空运动模式。在此基础上，小波扩散模型（WDM）在小波潜空间上训练扩散模型，实现从潜变量生成自然运动序列。同时，提出小波空间塑形引导机制，优化去噪过程以增强与流形结构的一致性；并引入时序注意力引导机制，进一步提升预测精度。大量实验验证了该方法在多个基准上的有效性，展现出更高的预测准确率与更强的泛化能力。代码与模型将在录用后公开。
原文摘要 · Abstract (English)
Modeling temporal characteristics and the non-stationary dynamics of body movement plays a significant role in predicting human future motions. However, it is challenging to capture these features due to the subtle transitions involved in the complex human motions. This paper introduces MotionWavelet, a human motion prediction framework that utilizes Wavelet Transformation and studies human motion patterns in the spatial-frequency domain. In MotionWavelet, a Wavelet Diffusion Model (WDM) learns a Wavelet Manifold by applying Wavelet Transformation on the motion data therefore encoding the intricate spatial and temporal motion patterns. Once the Wavelet Manifold is built, WDM trains a diffusion model to generate human motions from Wavelet latent vectors. In addition to the WDM, MotionWavelet also presents a Wavelet Space Shaping Guidance mechanism to refine the denoising process to improve conformity with the manifold structure. WDM also develops Temporal Attention-Based Guidance to enhance prediction accuracy. Extensive experiments validate the effectiveness of MotionWavelet, demonstrating improved prediction accuracy and enhanced generalization across various benchmarks. Our code and models will be released upon acceptance.
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。