RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse

TL;DR

RMD is a training-free, retrieval-augmented baseline for human motion generation that improves generalization and out-of-distribution performance by leveraging external databases and pre-trained diffusion models.

Contribution

It introduces a simple, training-free method that enhances motion generation generalization using retrieval and pre-trained diffusion models, without additional training.

Findings

Achieves state-of-the-art results without training.

Excels on out-of-distribution motion data.

Flexible database replacement and motion recombination.

Abstract

While motion generation has made substantial progress, its practical application remains constrained by dataset diversity and scale, limiting its ability to handle out-of-distribution scenarios. To address this, we propose a simple and effective baseline, RMD, which enhances the generalization of motion generation through retrieval-augmented techniques. Unlike previous retrieval-based methods, RMD requires no additional training and offers three key advantages: (1) the external retrieval database can be flexibly replaced; (2) body parts from the motion database can be reused, with an LLM facilitating splitting and recombination; and (3) a pre-trained motion diffusion model serves as a prior to improve the quality of motions obtained through retrieval and direct combination. Without any training, RMD achieves state-of-the-art performance, with notable advantages on out-of-distribution data.