InterSyn: Interleaved Learning for Dynamic Motion Synthesis in the Wild
This addresses the challenge of synthesizing natural and coordinated multi-character motions for applications in animation or simulation, representing an incremental improvement over existing approaches.
The paper tackles the problem of generating realistic interaction motions by learning from integrated solo and multi-person dynamics, resulting in motion sequences with higher text-to-motion alignment and improved diversity compared to recent methods.
We present Interleaved Learning for Motion Synthesis (InterSyn), a novel framework that targets the generation of realistic interaction motions by learning from integrated motions that consider both solo and multi-person dynamics. Unlike previous methods that treat these components separately, InterSyn employs an interleaved learning strategy to capture the natural, dynamic interactions and nuanced coordination inherent in real-world scenarios. Our framework comprises two key modules: the Interleaved Interaction Synthesis (INS) module, which jointly models solo and interactive behaviors in a unified paradigm from a first-person perspective to support multiple character interactions, and the Relative Coordination Refinement (REC) module, which refines mutual dynamics and ensures synchronized motions among characters. Experimental results show that the motion sequences generated by InterSyn exhibit higher text-to-motion alignment and improved diversity compared with recent methods, setting a new benchmark for robust and natural motion synthesis. Additionally, our code will be open-sourced in the future to promote further research and development in this area.