Poster
M GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Mingshuang Luo · RuiBing Hou · Zhuo Li · Hong Chang · Zimo Liu · Yaowei Wang · Shiguang Shan
Abstract:
This paper presents M GPT, an advanced ultimodal, ultitask framework for otion comprehension and generation. M GPT operates on three fundamental principles. The first focuses on creating a unified representation space for various motion-relevant modalities. We employ discrete vector quantization for multimodal conditional signals, such as text, music and motion/dance, enabling seamless integration into a large language model (LLM) with a single vocabulary.The second involves modeling motion generation directly in the raw motion space. This strategy circumvents the information loss associated with a discrete tokenizer, resulting in more detailed and comprehensive motion generation. Third, M GPT learns to model the connections and synergies among various motion-relevant tasks. Text, the most familiar and well-understood modality for LLMs, is utilized as a bridge to establish connections between different motion tasks, facilitating mutual reinforcement. To our knowledge, M GPT is the first model capable of comprehending and generating motions based on multiple signals.Extensive experiments highlight M GPT's superior performance across various motion-relevant tasks and its powerful zero-shot generalization capabilities for extremely challenging tasks. Project page: \url{https://github.com/luomingshuang/M3GPT}.
Chat is not available.