X-MoGen: Unified Motion Generation across Humans and Animals

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Xuan, Ruan, Kai, Qian, Liyang, Guo, Zhizhi, Su, Chang, Wang, Gaoang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911267376070656
author Wang, Xuan
Ruan, Kai
Qian, Liyang
Guo, Zhizhi
Su, Chang
Wang, Gaoang
author_facet Wang, Xuan
Ruan, Kai
Qian, Liyang
Guo, Zhizhi
Su, Chang
Wang, Gaoang
contents Text-driven motion generation has attracted increasing attention due to its broad applications in virtual reality, animation, and robotics. While existing methods typically model human and animal motion separately, a joint cross-species approach offers key advantages, such as a unified representation and improved generalization. However, morphological differences across species remain a key challenge, often compromising motion plausibility. To address this, we propose X-MoGen, the first unified framework for cross-species text-driven motion generation covering both humans and animals. X-MoGen adopts a two-stage architecture. First, a conditional graph variational autoencoder learns canonical T-pose priors, while an autoencoder encodes motion into a shared latent space regularized by morphological loss. In the second stage, we perform masked motion modeling to generate motion embeddings conditioned on textual descriptions. During training, a morphological consistency module is employed to promote skeletal plausibility across species. To support unified modeling, we construct UniMo4D, a large-scale dataset of 115 species and 119k motion sequences, which integrates human and animal motions under a shared skeletal topology for joint training. Extensive experiments on UniMo4D demonstrate that X-MoGen outperforms state-of-the-art methods on both seen and unseen species.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05162
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle X-MoGen: Unified Motion Generation across Humans and Animals
Wang, Xuan
Ruan, Kai
Qian, Liyang
Guo, Zhizhi
Su, Chang
Wang, Gaoang
Computer Vision and Pattern Recognition
Text-driven motion generation has attracted increasing attention due to its broad applications in virtual reality, animation, and robotics. While existing methods typically model human and animal motion separately, a joint cross-species approach offers key advantages, such as a unified representation and improved generalization. However, morphological differences across species remain a key challenge, often compromising motion plausibility. To address this, we propose X-MoGen, the first unified framework for cross-species text-driven motion generation covering both humans and animals. X-MoGen adopts a two-stage architecture. First, a conditional graph variational autoencoder learns canonical T-pose priors, while an autoencoder encodes motion into a shared latent space regularized by morphological loss. In the second stage, we perform masked motion modeling to generate motion embeddings conditioned on textual descriptions. During training, a morphological consistency module is employed to promote skeletal plausibility across species. To support unified modeling, we construct UniMo4D, a large-scale dataset of 115 species and 119k motion sequences, which integrates human and animal motions under a shared skeletal topology for joint training. Extensive experiments on UniMo4D demonstrate that X-MoGen outperforms state-of-the-art methods on both seen and unseen species.
title X-MoGen: Unified Motion Generation across Humans and Animals
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.05162