MoRAG——面向人体运动的多融合检索增强生成
MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion
AI总结：
本研究提出MoRAG多部件融合检索增强生成策略，通过LLM优化检索、多部件检索及空间组合生成样本，可作为即插即用模块提升文本驱动人体运动扩散模型的性能。
摘要：
我们提出了MoRAG，一种基于多部件融合的新型检索增强生成策略，用于文本驱动的人体运动生成。该方法通过利用改进的运动检索流程获取的额外知识，增强运动扩散模型的性能。我们通过有效提示大语言模型（LLM），解决了运动检索中的拼写错误与表述改写问题。本方法采用多部件检索策略，提升了运动检索在语言空间中的泛化能力。我们通过对检索到的运动进行空间组合，生成多样化样本；此外，利用低层、部件特定的运动信息，能够为未见过的文本描述构建运动样本。实验表明，该框架可作为即插即用模块，提升运动扩散模型的性能。代码、预训练模型与样例视频可在https://motion-rag.github.io/获取。
英文摘要：
We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos are available at: https://motion-rag.github.io/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
