发表机构
College of Computing and Data Science; Nanyang Technological University（计算与数据科学学院; 南洋理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对人-物-场景配对数据稀缺的问题，提出MAMHOI方法，通过可供性介导分解场景感知HOI生成，实验显示其可减少物体-场景穿透，提升交互质量与物理可行性。
AI 中文摘要
在复杂3D场景中生成逼真的人-物交互（HOI）需要两种互补能力：推理环境中交互的可行性，以及合成逼真的人-物运动。然而，这两种能力的大规模联合监督数据极为稀缺。人-场景数据集提供了丰富的环境感知运动信息，而人-物数据集则捕获了详细的交互动态，但配对的人-物-场景数据仍然匮乏。我们提出MAMHOI，一种通过可供性介导的场景感知人-物交互生成分解方法。MAMHOI通过场景理解与运动合成之间显式的运动-可供性接口，分解场景感知HOI生成：一个场景条件模型首先预测交互可被可行执行的位置与方式，随后一个可供性条件HOI模型生成对应的人-物运动。这种分解使场景理解与交互动态能从互补的监督源中学习，无需配对的人-物-场景数据。在复杂室内环境中的实验表明，MAMHOI减少了物体-场景穿透，同时更好地保留了人-物交互质量，生成了更逼真、物理可行的场景感知交互。项目页面：this https URL
英文摘要
Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion. However, supervision for these capabilities is rarely available jointly at scale. Human-scene datasets provide rich information about environment-aware motion, while human-object datasets capture detailed interaction dynamics, yet paired human-object-scene data remain scarce. We present MAMHOI, an affordance-mediated factorization for scene-aware human-object interaction generation. MAMHOI factorizes scene-aware HOI generation through an explicit motion-affordance interface between scene understanding and motion synthesis: a scene-conditioned model first predicts where and how an interaction can be feasibly executed, and an affordance-conditioned HOI model then generates the corresponding human-object motion. This factorization allows scene understanding and interaction dynamics to be learned from complementary sources of supervision without requiring paired human-object-scene data. Experiments in complex indoor environments show that MAMHOI reduces object--scene penetration while better preserving human--object interaction quality, yielding more realistic and physically feasible scene-aware interactions. Project page: https://leimingyuan.github.io/MAMHOI-project-page/
CommentsProject page: https://leimingyuan.github.io/MAMHOI-project-page/
