PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yujie, Zhang, Zhichao, Chen, Jiazhou, Wu, Zichao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912797052370944
author Yang, Yujie
Zhang, Zhichao
Chen, Jiazhou
Wu, Zichao
author_facet Yang, Yujie
Zhang, Zhichao
Chen, Jiazhou
Wu, Zichao
contents Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose PartMotionEdit, a novel fine-grained motion editing framework that operates via part-level semantic modulation. The core of PartMotionEdit is a Part-aware Motion Modulation (PMM) module, which builds upon a predefined five-part body decomposition. PMM dynamically predicts time-varying modulation weights for each body part, enabling precise and interpretable editing of local motions. To guide the training of PMM, we also introduce a part-level similarity curve supervision mechanism enhanced with dual-layer normalization. This mechanism assists PMM in learning semantically consistent and editable distributions across all body parts. Furthermore, we design a Bidirectional Motion Interaction (BMI) module. It leverages bidirectional cross-modal attention to achieve more accurate semantic alignment between textual instructions and motion semantics. Extensive quantitative and qualitative evaluations on a well-known benchmark demonstrate that PartMotionEdit outperforms the state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_24200
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation
Yang, Yujie
Zhang, Zhichao
Chen, Jiazhou
Wu, Zichao
Graphics
Existing text-driven 3D human motion editing methods have demonstrated significant progress, but are still difficult to precisely control over detailed, part-specific motions due to their global modeling nature. In this paper, we propose PartMotionEdit, a novel fine-grained motion editing framework that operates via part-level semantic modulation. The core of PartMotionEdit is a Part-aware Motion Modulation (PMM) module, which builds upon a predefined five-part body decomposition. PMM dynamically predicts time-varying modulation weights for each body part, enabling precise and interpretable editing of local motions. To guide the training of PMM, we also introduce a part-level similarity curve supervision mechanism enhanced with dual-layer normalization. This mechanism assists PMM in learning semantically consistent and editable distributions across all body parts. Furthermore, we design a Bidirectional Motion Interaction (BMI) module. It leverages bidirectional cross-modal attention to achieve more accurate semantic alignment between textual instructions and motion semantics. Extensive quantitative and qualitative evaluations on a well-known benchmark demonstrate that PartMotionEdit outperforms the state-of-the-art methods.
title PartMotionEdit: Fine-Grained Text-Driven 3D Human Motion Editing via Part-Level Modulation
topic Graphics
url https://arxiv.org/abs/2512.24200