Fine-Grained Body Part Control in Text-Driven Motion Synthesis with Interactive Intention

Text-to-motion has widespread applications in VR/AR, games, filmmaking, and robotics. In real-world scenarios, humans frequently initiate interactions with the surrounding environment using specific body parts. In this work, we introduce BOCO, a novel method for fine-grained BOdy part COntrol in text-driven human motion synthesis with interactive intention. BOCO employs a decoupled strategy to extract body part movements and leverages large language models to capture corresponding part-level semantics described in text. Additionally, BOCO introduces a spatial coherence module based on a part-based graph structure to ensure semantic accuracy and spatial consistency. We developed a specialized dataset from HUMANML3D for training and evaluation. Experiments demonstrate that BOCO significantly enhances nuanced, accurate, and adaptable text-to-motion generation. By focusing on human-centric interactive intentions, BOCO is better suited for general and flexible interaction scenarios, paving the way for broader interaction applications as object inference and simulation technologies advance.