MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909405950246912 |
|---|---|
| author | Feng, Yuming Dou, Zhiyang Chen, Ling-Hao Liu, Yuan Li, Tianyu Wang, Jingbo Cao, Zeyu Wang, Wenping Komura, Taku Liu, Lingjie |
| author_facet | Feng, Yuming Dou, Zhiyang Chen, Ling-Hao Liu, Yuan Li, Tianyu Wang, Jingbo Cao, Zeyu Wang, Wenping Komura, Taku Liu, Lingjie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_16964 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning Feng, Yuming Dou, Zhiyang Chen, Ling-Hao Liu, Yuan Li, Tianyu Wang, Jingbo Cao, Zeyu Wang, Wenping Komura, Taku Liu, Lingjie Computer Vision and Pattern Recognition Graphics Robotics 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. |
| title | MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning |
| topic | Computer Vision and Pattern Recognition Graphics Robotics |
| url | https://arxiv.org/abs/2411.16964 |