arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.12456cs.CVcs.RO
收藏

贝叶斯优化的一步扩散模型结合知识蒸馏用于实时3D人体运动预测

Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction

Texas A&M University(德克萨斯农工大学)

Sibo Tian, Minghui Zheng, Xiao Liang

AI总结:

针对扩散模型预测人体运动速度慢的问题,提出结合知识蒸馏与贝叶斯优化训练一步MLP扩散模型,实现实时预测且性能不降。

摘要:

人体运动预测是人机协作(HRC)的基石,因为机器人需要根据过去的运动线索推断人类工人的未来动作,以主动规划其运动,确保紧密协作场景中的安全。扩散模型在预测具有合理多样性的高质量运动样本方面表现出卓越性能,但其生成过程缓慢,需要多次模型评估,阻碍了实际应用。为了实现实时预测,在本工作中,我们提出使用知识蒸馏和贝叶斯优化训练一个基于多层感知器(MLP)的一步扩散模型用于运动预测。我们的方法包含两个步骤。首先,我们将预训练的基于扩散的运动预测器TransFusion直接蒸馏为具有相同去噪器架构的一步扩散模型。然后,为进一步减少推理时间,我们移除原始去噪器中计算昂贵的组件,并再次使用知识蒸馏将获得的一步扩散模型蒸馏为仅基于MLP的更小模型。贝叶斯优化用于调整训练较小扩散模型的超参数。在基准数据集上进行了广泛的实验研究,我们的模型能够显著提高推理速度,实现实时预测,且性能无明显下降。

英文摘要:

Human motion prediction is a cornerstone of human-robot collaboration (HRC), as robots need to infer the future movements of human workers based on past motion cues to proactively plan their motion, ensuring safety in close collaboration scenarios. The diffusion model has demonstrated remarkable performance in predicting high-quality motion samples with reasonable diversity, but suffers from a slow generative process which necessitates multiple model evaluations, hindering real-world applications. To enable real-time prediction, in this work, we propose training a one-step multi-layer perceptron-based (MLP-based) diffusion model for motion prediction using knowledge distillation and Bayesian optimization. Our method contains two steps. First, we distill a pretrained diffusion-based motion predictor, TransFusion, directly into a one-step diffusion model with the same denoiser architecture. Then, to further reduce the inference time, we remove the computationally expensive components from the original denoiser and use knowledge distillation once again to distill the obtained one-step diffusion model into an even smaller model based solely on MLPs. Bayesian optimization is used to tune the hyperparameters for training the smaller diffusion model. Extensive experimental studies are conducted on benchmark datasets, and our model can significantly improve the inference speed, achieving real-time prediction without noticeable degradation in performance.

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。

↑