Spatial-Temporal Multi-Scale Quantization for Flexible Motion Generation
This work addresses the problem of flexible motion generation for applications in human motion modeling, though it appears incremental in improving existing quantization approaches.
The paper tackles the limitations of current motion representations by introducing MSQ, a multi-scale quantization method that compresses motion sequences into discrete tokens across spatial and temporal dimensions, enabling seamless composition and outperforming baselines on various benchmarks.
Despite significant advancements in human motion generation, current motion representations, typically formulated as discrete frame sequences, still face two critical limitations: (i) they fail to capture motion from a multi-scale perspective, limiting the capability in complex patterns modeling; (ii) they lack compositional flexibility, which is crucial for model's generalization in diverse generation tasks. To address these challenges, we introduce MSQ, a novel quantization method that compresses the motion sequence into multi-scale discrete tokens across spatial and temporal dimensions. MSQ employs distinct encoders to capture body parts at varying spatial granularities and temporally interpolates the encoded features into multiple scales before quantizing them into discrete tokens. Building on this representation, we establish a generative mask modeling model to effectively support motion editing, motion control, and conditional motion generation. Through quantitative and qualitative analysis, we show that our quantization method enables the seamless composition of motion tokens without requiring specialized design or re-training. Furthermore, extensive evaluations demonstrate that our approach outperforms existing baseline methods on various benchmarks.