全监督运动编辑：通过正负学习平衡变化与不变性
Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning
论文提出的正负学习统一监督范式（回顾式特征监督 + 基于源-目标相似度的运动保持 + 三元组语义对齐）可直接迁移到图像/视频编辑扩散模型中，用于缓解编辑时目标区域改动不足与未编辑区域被破坏之间的权衡。
原文依据 The key challenge lies in balancing change (i.e. precisely editing target regions) and invariance (i.e. preserving unedited parts).
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于文本的人体运动编辑旨在根据自然语言指令修改已有运动序列，同时保持原始运动的一致性。现有基于扩散的方法往往依赖启发式相似性线索或粗粒度的全局条件，导致运动失真和语义对齐欠佳。核心挑战在于平衡变化（即精确编辑目标区域）与不变性（即保留未编辑部分）。为应对这一挑战，我们提出一种全监督正负学习框架，命名为 OmniME。该方法集成了三个互补组件：(1) 回顾式特征监督，在 Transformer 各层之间强制实现由粗到细的一致性；(2) 运动保持机制，依据源-目标相似度关注细微变化；(3) 基于三元组的语义对齐，增强文本与运动之间的对应关系。这些组件共同构成一个统一的监督范式，以平衡变化与不变性。在 MotionFix 和 STANCE Adjustment 数据集上的大量实验表明，OmniME 在编辑对齐方面达到最优性能，验证了该统一学习框架的有效性。我们的源代码与模型已发布于：https://github.com/rocket-ycyer/OmniME.git。
英文原文摘要 1353 字符
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 accoding 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