Shape Conditioned Human Motion Generation with Diffusion Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xue, Kebing, Seo, Hyewon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909197951565824
author Xue, Kebing
Seo, Hyewon
author_facet Xue, Kebing
Seo, Hyewon
contents Human motion synthesis is an important task in computer graphics and computer vision. While focusing on various conditioning signals such as text, action class, or audio to guide the generation process, most existing methods utilize skeleton-based pose representation, requiring additional skinning to produce renderable meshes. Given that human motion is a complex interplay of bones, joints, and muscles, considering solely the skeleton for generation may neglect their inherent interdependency, which can limit the variability and precision of the generated results. To address this issue, we propose a Shape-conditioned Motion Diffusion model (SMD), which enables the generation of motion sequences directly in mesh format, conditioned on a specified target mesh. In SMD, the input meshes are transformed into spectral coefficients using graph Laplacian, to efficiently represent meshes. Subsequently, we propose a Spectral-Temporal Autoencoder (STAE) to leverage cross-temporal dependencies within the spectral domain. Extensive experimental evaluations show that SMD not only produces vivid and realistic motions but also achieves competitive performance in text-to-motion and action-to-motion tasks when compared to state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06778
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Shape Conditioned Human Motion Generation with Diffusion Model
Xue, Kebing
Seo, Hyewon
Computer Vision and Pattern Recognition
Graphics
Human motion synthesis is an important task in computer graphics and computer vision. While focusing on various conditioning signals such as text, action class, or audio to guide the generation process, most existing methods utilize skeleton-based pose representation, requiring additional skinning to produce renderable meshes. Given that human motion is a complex interplay of bones, joints, and muscles, considering solely the skeleton for generation may neglect their inherent interdependency, which can limit the variability and precision of the generated results. To address this issue, we propose a Shape-conditioned Motion Diffusion model (SMD), which enables the generation of motion sequences directly in mesh format, conditioned on a specified target mesh. In SMD, the input meshes are transformed into spectral coefficients using graph Laplacian, to efficiently represent meshes. Subsequently, we propose a Spectral-Temporal Autoencoder (STAE) to leverage cross-temporal dependencies within the spectral domain. Extensive experimental evaluations show that SMD not only produces vivid and realistic motions but also achieves competitive performance in text-to-motion and action-to-motion tasks when compared to state-of-the-art methods.
title Shape Conditioned Human Motion Generation with Diffusion Model
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2405.06778