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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liao, Zhouyingcheng, Zhang, Mingyuan, Wang, Wenjia, Yang, Lei, Komura, Taku
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915049726017536
author Liao, Zhouyingcheng
Zhang, Mingyuan
Wang, Wenjia
Yang, Lei
Komura, Taku
author_facet Liao, Zhouyingcheng
Zhang, Mingyuan
Wang, Wenjia
Yang, Lei
Komura, Taku
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_04343
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse
Liao, Zhouyingcheng
Zhang, Mingyuan
Wang, Wenjia
Yang, Lei
Komura, Taku
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
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.
title RMD: A Simple Baseline for More General Human Motion Generation via Training-free Retrieval-Augmented Motion Diffuse
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2412.04343