VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
Haidong Xu, Guangwei Xu, Zhedong Zheng, Xiatian Zhu, Wei Ji, Xiangtai Li, Ruijie Guo, Meishan Zhang
Abstract
This paper introduces **VimoRAG**, a novel video-based retrieval-augmented motion generation framework for motion large language models (LLMs). As motion LLMs face severe out-of-domain/out-of-vocabulary issues due to limited annotated data, **VimoRAG** leverages large-scale in-the-wild video databases to enhance 3D motion generation by retrieving relevant 2D human motion signals. While video-based motion RAG is nontrivial, we address two key bottlenecks: (1) developing an effective motion-centered video retrieval model that distinguishes human poses and actions, and (2) mitigating the issue of error propagation caused by suboptimal retrieval results. We design the Gemini Motion Video Retriever mechanism and the Motion-centric Dual-alignment DPO Trainer, enabling effective retrieval and generation processes. Experimental results show that **VimoRAG** significantly boosts the performance of motion LLMs constrained to text-only input.
BibTeX
@inproceedings{
xu2025vimorag,
title={Vimo{RAG}: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models},
author={Haidong Xu and Guangwei Xu and Zhedong Zheng and Xiatian Zhu and Wei Ji and Xiangtai Li and Ruijie Guo and Meishan Zhang and Min zhang and Hao Fei},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=0enwkxV3sx}
}