T2M-X: Learning Expressive Text-to-Motion Generation from Partially Annotated Data
This work addresses a limitation in animation production and AR/VR experiences by enabling expressive text-to-motion generation, though it is incremental as it builds on prior methods with a novel approach to handle data constraints.
The paper tackles the problem of generating whole-body humanoid animation from text prompts, which existing methods fail to do by excluding facial expressions and hand movements, and it achieves significant improvements over baselines both quantitatively and qualitatively.
The generation of humanoid animation from text prompts can profoundly impact animation production and AR/VR experiences. However, existing methods only generate body motion data, excluding facial expressions and hand movements. This limitation, primarily due to a lack of a comprehensive whole-body motion dataset, inhibits their readiness for production use. Recent attempts to create such a dataset have resulted in either motion inconsistency among different body parts in the artificially augmented data or lower quality in the data extracted from RGB videos. In this work, we propose T2M-X, a two-stage method that learns expressive text-to-motion generation from partially annotated data. T2M-X trains three separate Vector Quantized Variational AutoEncoders (VQ-VAEs) for body, hand, and face on respective high-quality data sources to ensure high-quality motion outputs, and a Multi-indexing Generative Pretrained Transformer (GPT) model with motion consistency loss for motion generation and coordination among different body parts. Our results show significant improvements over the baselines both quantitatively and qualitatively, demonstrating its robustness against the dataset limitations.