VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models
This work addresses a domain-specific problem for researchers and practitioners in motion generation, offering an incremental improvement by integrating retrieval mechanisms to overcome data limitations.
The paper tackles the problem of out-of-domain issues in motion large language models (LLMs) by introducing VimoRAG, a video-based retrieval-augmented framework that enhances 3D motion generation using large-scale video databases, resulting in significant performance boosts for text-only motion LLMs.
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. All the resources are available at https://walkermitty.github.io/VimoRAG/