InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE
This addresses the need for realistic human interaction generation in applications like virtual reality and robotics, representing a novel method for a known bottleneck.
The paper tackles the problem of generating high-quality 3D human interactions that preserve individual characteristics and adhere to textual descriptions, achieving state-of-the-art performance with reductions in FID scores by 9% on the InterHuman dataset and 22% on InterX.
Generating high-quality human interactions holds significant value for applications like virtual reality and robotics. However, existing methods often fail to preserve unique individual characteristics or fully adhere to textual descriptions. To address these challenges, we introduce InterMoE, a novel framework built on a Dynamic Temporal-Selective Mixture of Experts. The core of InterMoE is a routing mechanism that synergistically uses both high-level text semantics and low-level motion context to dispatch temporal motion features to specialized experts. This allows experts to dynamically determine the selection capacity and focus on critical temporal features, thereby preserving specific individual characteristic identities while ensuring high semantic fidelity. Extensive experiments show that InterMoE achieves state-of-the-art performance in individual-specific high-fidelity 3D human interaction generation, reducing FID scores by 9% on the InterHuman dataset and 22% on InterX.