论文概要
Uni-Inter 用 Unified Interactive Volume 统一表示人—人、人—物和人—场景交互，并逐关节进行概率式动作预测，让一个 task-agnostic 模型能够推理异构和复合交互上下文。
研究问题
交互动作生成通常按任务分别设计模型和表示，导致人、物体、场景及其组合之间难以共享知识与泛化。
论文贡献
- 用单一架构支持 human–human、human–object 和 human–scene motion generation。
- 提出 Unified Interactive Volume，把异构交互实体编码到共享体积场中。
- 将动作生成表述为 joint-wise probabilistic prediction，以建模空间依赖和上下文行为。
证据与评测范围
实验覆盖三类代表性交互任务，报告了有竞争力的结果以及对新实体组合的泛化；具体数据集、指标与比较应以 ACM 正式论文为准。
适用范围与局限
共享表示不意味着已经解决所有交互类型或任意未见组合；泛化结论受已评测任务、实体编码和动作分布范围约束。
Related work 定位
Uni-Inter 是交互动作合成中的统一表示方法。它不只是做多任务训练，UIV 还为异构交互提供了共同的空间关系推理场。
Related Work 表述
Liu 等提出 Uni-Inter，在 Unified Interactive Volume 中统一编码人物、物体和场景实体，并通过逐关节概率预测生成三维交互动作。
这是一段用于说明论文定位的简洁中性表述。
论文官方英文摘要
We present Uni-Inter, a unified framework for human motion generation that supports a wide range of interaction scenarios: including human-human, human-object, and human-scene-within a single, task-agnostic architecture. In contrast to existing methods that rely on task-specific designs and exhibit limited generalization, Uni-Inter introduces the Unified Interactive Volume (UIV), a volumetric representation that encodes heterogeneous interactive entities into a shared spatial field. This enables consistent relational reasoning and compound interaction modeling. Motion generation is formulated as joint-wise probabilistic prediction over the UIV, allowing the model to capture fine-grained spatial dependencies and produce coherent, context-aware behaviors. Experiments across three representative interaction tasks demonstrate that Uni-Inter achieves competitive performance and generalizes well to novel combinations of entities. These results suggest that unified modeling of compound interactions offers a promising direction for scalable motion synthesis in complex environments.
摘要仅用于学术识别，版权仍归论文作者或出版方所有，不属于本页 CC BY 许可范围。
依据与出处
| 核对内容 | 论文中的位置 |
|---|---|
| 问题陈述 | Abstract |
| 方法与贡献 | Abstract; Unified Interactive Volume and probabilistic prediction sections |
| 评测结论 | Abstract; experiments across three interaction tasks |
主要核验来源: ACM version of record (SIGGRAPH Asia 2025 version of record; arXiv:2511.13032v1 used for accessible abstract).
如何引用
科研结论应引用论文本身；只有在复用本站原创解读时才引用本页。
Sheng Liu, Yuanzhi Liang, Jiepeng Wang, Sidan Du, Chi Zhang, and Xuelong Li. “Uni-Inter: Unifying 3D Human Motion Synthesis Across Diverse Interaction Contexts.” Proceedings of the SIGGRAPH Asia 2025 Conference Papers (2025), 1-11. https://doi.org/10.1145/3757377.3763954.
复用许可
本页原创解读采用 CC BY 4.0：复用时须署名并链接本页。论文标题、摘要、图表和书目信息不在此许可范围内，仍保留原有权利。 Creative Commons Attribution 4.0 International.