Guardado en:
Detalles Bibliográficos
Autores principales: Jiang, Lei, Wei, Ye, Ni, Hao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2501.19083
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916646725091328
author Jiang, Lei
Wei, Ye
Ni, Hao
author_facet Jiang, Lei
Wei, Ye
Ni, Hao
contents Diffusion models have become a popular choice for human motion synthesis due to their powerful generative capabilities. However, their high computational complexity and large sampling steps pose challenges for real-time applications. Fortunately, the Consistency Model (CM) provides a solution to greatly reduce the number of sampling steps from hundreds to a few, typically fewer than four, significantly accelerating the synthesis of diffusion models. However, applying CM to text-conditioned human motion synthesis in latent space yields unsatisfactory generation results. In this paper, we introduce \textbf{MotionPCM}, a phased consistency model-based approach designed to improve the quality and efficiency for real-time motion synthesis in latent space. Experimental results on the HumanML3D dataset show that our model achieves real-time inference at over 30 frames per second in a single sampling step while outperforming the previous state-of-the-art with a 38.9\% improvement in FID. The code will be available for reproduction.
format Preprint
id arxiv_https___arxiv_org_abs_2501_19083
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
Jiang, Lei
Wei, Ye
Ni, Hao
Computer Vision and Pattern Recognition
Diffusion models have become a popular choice for human motion synthesis due to their powerful generative capabilities. However, their high computational complexity and large sampling steps pose challenges for real-time applications. Fortunately, the Consistency Model (CM) provides a solution to greatly reduce the number of sampling steps from hundreds to a few, typically fewer than four, significantly accelerating the synthesis of diffusion models. However, applying CM to text-conditioned human motion synthesis in latent space yields unsatisfactory generation results. In this paper, we introduce \textbf{MotionPCM}, a phased consistency model-based approach designed to improve the quality and efficiency for real-time motion synthesis in latent space. Experimental results on the HumanML3D dataset show that our model achieves real-time inference at over 30 frames per second in a single sampling step while outperforming the previous state-of-the-art with a 38.9\% improvement in FID. The code will be available for reproduction.
title MotionPCM: Real-Time Motion Synthesis with Phased Consistency Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.19083