Synthesizing semantic-aware, long-horizon, human-object interaction is critical to simulate realistic human behaviors. In this work, we address the challenging problem of generating synchronized object motion and human motion guided by language descriptions in 3D scenes. We propose Controllable Human-Object Interaction Synthesis (CHOIS), an approach that generates object motion and human motion simultaneously using a conditional diffusion model given a language description, initial object and human states, and sparse object waypoints. While language descriptions inform style and intent, waypoints ground the motion in the scene and can be effectively extracted using high-level planning methods. Naively applying a diffusion model fails to predict object motion aligned with the input waypoints and cannot ensure the realism of interactions that require precise hand-object contact and appropriate contact grounded by the floor. To overcome these problems, we introduce an object geometry loss as additional supervision to improve the matching between generated object motion and input object waypoints. In addition, we design guidance terms to enforce contact constraints during the sampling process of the trained diffusion model.

在这项工作中，我们提出了一种名为Controllable Human-Object Interaction Synthesis (CHOIS)的方法，它利用语言描述、初始物体和人体状态以及稀疏的物体路点同时生成物体运动和人体动作，通过引入物体几何损失和设计指导项来提高生成的物体运动和输入物体路点之间的匹配，并确保与地板接触的精确手-物体接触和适当接触的真实性。

可控制的人-物互动合成