面向人-物交互合成的解耦生成建模
Decoupled Generative Modeling for Human-Object Interaction Synthesis
将 HOI 合成解耦为「轨迹生成 + 动作生成」两阶段，并用关注远端关节动力学的判别器做对抗训练，可复用于人体动作生成与具身控制中的接触真实性问题。
原文依据 separates path planning and action synthesis
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论合成逼真的人-物交互（HOI）对三维计算机视觉与机器人学至关重要，是动画与具身控制的基础。现有方法通常需要人工指定中间路点，并将所有优化目标置于单一网络上，这增加了复杂度、降低了灵活性，并导致人体与物体运动不同步或相互穿透等错误。为解决这些问题，我们提出面向人-物交互合成的解耦生成建模（DecHOI），将路径规划与动作合成分离。轨迹生成器首先在无预设路点的条件下生成人体与物体轨迹，动作生成器则以这些路径为条件合成细节动作。为进一步提升接触真实感，我们采用对抗训练，其判别器聚焦于远端关节的动力学。该框架还对运动的交互对象进行建模，支持动态场景中具有响应性的长序列规划，同时保持规划一致性。在两个基准 FullBodyManipulation 与 3D-FUTURE 上，DecHOI 在多数定量指标与定性评估上均优于先前方法，感知研究同样更偏好我们的结果。
英文原文摘要 1246 字符
Synthesizing realistic human-object interaction (HOI) is essential for 3D computer vision and robotics, underpinning animation and embodied control. Existing approaches often require manually specified intermediate waypoints and place all optimization objectives on a single network, which increases complexity, reduces flexibility, and leads to errors such as unsynchronized human and object motion or penetration. To address these issues, we propose Decoupled Generative Modeling for Human-Object Interaction Synthesis (DecHOI), which separates path planning and action synthesis. A trajectory generator first produces human and object trajectories without prescribed waypoints, and an action generator conditions on these paths to synthesize detailed motions. To further improve contact realism, we employ adversarial training with a discriminator that focuses on the dynamics of distal joints. The framework also models a moving counterpart and supports responsive, long-sequence planning in dynamic scenes, while preserving plan consistency. Across two benchmarks, FullBodyManipulation and 3D-FUTURE, DecHOI surpasses prior methods on most quantitative metrics and qualitative evaluations, and perceptual studies likewise prefer our results.