Decoupled Generative Modeling for Human-Object Interaction Synthesis
This addresses the need for more flexible and error-free human-object interaction synthesis in 3D computer vision and robotics, with incremental improvements over existing approaches.
The paper tackles the problem of synthesizing realistic human-object interactions by proposing DecHOI, which decouples path planning and action synthesis to avoid errors like unsynchronized motion, and it outperforms prior methods on benchmarks such as FullBodyManipulation and 3D-FUTURE in quantitative and qualitative evaluations.
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.