打开动作之门：面向开放词表动作生成的原子动作分解与重组
Open the Motion Door: Atomic Motion Decomposition and Recomposition for Open-Vocabulary Motion Generation
把开放词表文本拆成可复用的原子动作单元再重组，这一「分解-重组」思路可直接迁移到开放词表视频生成、组合式动作合成与长时序动作拼接，缓解域外文本泛化差的问题。
原文依据 many motions share a common set of underlying atomic motions--that is, simple, reusable body-part movements
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到动作生成是计算机视觉中的一项基础任务，旨在根据自然语言描述合成三维人体动作序列。然而，由于现有数据集规模与多样性有限，直接学习从原始文本到动作映射的模型往往难以泛化到域外文本输入。我们观察到，尽管高层动作语义差异很大，许多动作共享一组共同的底层原子动作——即简单、可复用的身体部位运动。基于这一观察，我们提出了一种面向开放词表文本到动作生成的原子动作分解与重组框架。该方法包含两个关键组件：一个文本分解模块，将域外描述解析为原子动作单元；以及一个原子重组模块，将这些单元整合以生成最终的动作序列。我们的模型在域内 HumanML3D 数据集上取得了有竞争力的性能，并在两个域外数据集（IDEA400 与 Mixamo）上的大量实验表明，我们的方法在开放词表动作生成上大幅优于最优方法。
英文原文摘要 1184 字符
Text-to-motion generation is a fundamental task in computer vision, aiming to synthesize 3D human motion sequences from natural language descriptions. However, due to the limited scale and diversity of existing datasets, models trained to directly map raw text to motion often struggle to generalize to out-of-domain textual inputs. We observe that although high-level motion semantics vary widely, many motions share a common set of underlying atomic motions--that is, simple, reusable body-part movements. Building on this insight, we introduce an **Atomic Motion Decomposition and Recomposition** framework for open-vocabulary text-to-motion generation. Our approach consists of two key components: a **Textual Decomposition** module that parses out-of-domain descriptions into atomic motion units, and an **Atomic Recomposition** module that integrates these units to produce the final motion sequence. Our model achieves a competitive performance on the in-domain HumanML3D dataset, and extensive experiments on two out-of-domain datasets (IDEA400 and Mixamo) demonstrate that our method substantially outperforms state-of-the-art approaches in open-vocabulary motion generation.