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

TL;DR

PartMotionEdit introduces a fine-grained, part-level text-driven 3D human motion editing framework that enables precise, interpretable local motion control through semantic modulation and bidirectional interaction, outperforming existing methods.

Contribution

It proposes a novel part-aware modulation and interaction framework for detailed, controllable 3D motion editing guided by text, with new supervision mechanisms for semantic consistency.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Enables precise, interpretable local motion editing.

Demonstrates effective semantic alignment between text and motion.

Abstract

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.