Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jeon, Junhyuk, Hong, Seokhyeon, Noh, Junyong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918499589292032
author Jeon, Junhyuk
Hong, Seokhyeon
Noh, Junyong
author_facet Jeon, Junhyuk
Hong, Seokhyeon
Noh, Junyong
contents Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to as style. Recent approaches have tackled this challenge by attaching a style injection mechanism to a pretrained text-driven diffusion model. Existing stylization methods, however, either require style-specific fine-tuning of existing models or rely on heavy ControlNet-based architectures, limiting efficiency and generalization to unseen styles. We propose a lightweight style conditioning framework that dynamically modulates a pretrained diffusion model through hypernetwork-generated LoRA parameters. A style reference motion is encoded into a global style embedding, which is mapped by a hypernetwork to low-rank updates applied at each denoising step of the diffusion model. By structuring the style latent space with a supervised contrastive loss, our framework reliably captures diverse stylistic attributes, improves generalization to unseen styles, and supports optimization-based guidance without requiring predefined style categories. Experiments on the HumanML3D and 100STYLE datasets show state-of-the-art stylization results, while achieving improved stylization for unseen styles.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13333
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
Jeon, Junhyuk
Hong, Seokhyeon
Noh, Junyong
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of motion, commonly referred to as style. Recent approaches have tackled this challenge by attaching a style injection mechanism to a pretrained text-driven diffusion model. Existing stylization methods, however, either require style-specific fine-tuning of existing models or rely on heavy ControlNet-based architectures, limiting efficiency and generalization to unseen styles. We propose a lightweight style conditioning framework that dynamically modulates a pretrained diffusion model through hypernetwork-generated LoRA parameters. A style reference motion is encoded into a global style embedding, which is mapped by a hypernetwork to low-rank updates applied at each denoising step of the diffusion model. By structuring the style latent space with a supervised contrastive loss, our framework reliably captures diverse stylistic attributes, improves generalization to unseen styles, and supports optimization-based guidance without requiring predefined style categories. Experiments on the HumanML3D and 100STYLE datasets show state-of-the-art stylization results, while achieving improved stylization for unseen styles.
title Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
Machine Learning
url https://arxiv.org/abs/2605.13333