通过正负样本学习，实现动作编辑的精准修改与未编辑部分的稳定保留。
Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning
- 引入正负样本对比学习，统一优化编辑区域与保持区域的监督信号。
- 在两个数据集上达到当前最优的语义对齐效果，编辑准确率提升显著。
- 适合需要精细动作编辑且要求原动作结构不变的研究者和开发者。
基于文本的人体动作编辑旨在根据自然语言指令修改现有动作序列，同时保持原始动作的一致性。现有的基于扩散模型的方法通常依赖启发式相似性线索或粗粒度全局条件，导致动作失真和语义对齐不佳。核心挑战在于平衡‘改变’（精确编辑目标区域）与‘不变’（保留未编辑部分）。为此，我们提出一种全监督正负样本学习框架 OmniME。该方法包含三个互补组件：(1) 回溯特征监督，确保跨 Transformer 层的粗到细一致性；(2) 动作保持机制，根据源-目标相似性关注细微变化；(3) 三元组语义对齐，强化文本与动作的对应关系。三者共同构成统一的监督范式，有效平衡改变与不变性。在 MotionFix 与 STANCE Adjustment 数据集上的大量实验表明，OmniME 在编辑对齐性能上达到最新水平，验证了所提框架的有效性。代码与模型已开源：https://github.com/rocket-ycyer/OmniME.git。
原文摘要 · Abstract (English)
Text-based human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the consistency of the original motion. Existing diffusion-based approaches often rely on heuristic similarity cues or coarse global conditioning, leading to motion distortion and suboptimal semantic alignment. The key challenge lies in balancing change (i.e. precisely editing target regions) and invariance (i.e. preserving unedited parts). To handle such challenge, we propose an Omni-Supervised Positive-Negative Learning framework, named OmniME. Our method integrates three complementary components: (1) retrospective feature supervision that enforces coarse-to-fine consistency across transformer layers,(2) motion preservation mechanism that focuses on subtle variations according to the source-target similarity, and (3) triplet-based semantic alignment that strengthens text-motion correspondence. Together, these components form a unified supervision paradigm that balances change and invariance. Extensive experiments on the MotionFix and STANCE Adjustment datasets demonstrate that OmniME achieves state-of-the-art performance in editing alignment, validating the effectiveness of our unified learning framework. Our source codes and models have been released at: https://github.com/rocket-ycyer/OmniME.git
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。