面向文本驱动三维人体运动编辑的跨轴特征融合与关节级运动差异预测
Cross-Axis Feature Fusion with Joint-Wise Motion Difference Prediction for Text-Based 3D Human Motion Editing
把运动序列沿关节轴与时间轴分别用 Transformer 编码再做跨轴融合，并用 Soft-DTW 回归作为辅助任务定位「哪些关节该改」，这套轴分解+关节级差异预测的思路可直接迁移到人体动作生成、姿态序列编辑与细粒度时序定位任务。
原文依据 two axis-anchored transformers, which extract distinct features along the joint and time dimensions respectively, and a cross-axis fusion block
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文研究文本驱动的三维人体运动编辑，目标是在保留源运动风格与结构的同时，施加自然语言描述的编辑。MotionFix 数据集的发布推动了基于训练的扩散模型研究，这类模型直接从源运动与文本指令生成编辑后的运动。已有工作主要关注学习编辑应在时序上何时发生，而本文的目标是构建一个不仅理解这一时序层面、还能理解哪些具体关节应对变化负责的模型。为此，我们提出一种新颖架构以及一个辅助其训练的补充性辅助任务。该架构由两个轴锚定 Transformer 组成，分别沿关节维与时间维提取不同特征，并配有一个跨轴融合模块来整合这些表示。我们进一步引入一个辅助任务，训练关节锚定 Transformer 回归源与目标关节旋转之间的 Soft-DTW 距离。该目标使该模块学会理解哪些关节需要修改、哪些需要保留。在 MotionFix 数据集上的全面实验表明，本方法显著提升了与文本指令及源运动的语义对齐，以及生成运动的整体保真度，取得了最优结果。
英文原文摘要 1440 字符
We address text-based 3D human motion editing, where the goal is to preserve the style and structure of a source motion while applying edits described in natural language. The release of the MotionFix dataset has spurred active research into training-based diffusion models that directly generate an edited motion from a source motion and a text instruction. While previous works have focused primarily on learning when an edit should occur temporally, our goal is to create a model that understands not only this temporal aspect but also which specific joints are responsible for the change. Targeting this, we propose a novel architecture and a complementary auxiliary task to aid its training. Our architecture consists of two axis-anchored transformers, which extract distinct features along the joint and time dimensions respectively, and a cross-axis fusion block that integrates these representations. We further introduce an auxiliary task that trains the joint-anchored transformer to regress the Soft-DTW distance between source and target joint rotations. This objective teaches the module to understand which joints to modify and which to preserve. Through comprehensive experiments on the MotionFix dataset, we demonstrate that our method significantly improves semantic alignment with both the text instruction and the source motion, as well as the overall fidelity of the generated motion, achieving state-of-the-art results.