CVOct 16, 2025

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression

arXiv:2510.14954v17 citationsh-index: 11
Originality Incremental advance
AI Analysis

This work addresses the problem of generating coherent human motions from diverse inputs like text, speech, and music for applications in animation and human-computer interaction, representing an incremental improvement over existing methods.

The paper tackles whole-body multi-modal human motion generation by developing a continuous masked autoregressive motion transformer with gated linear attention and RMSNorm, integrated with DiT structure and AdaLN/cross-attention for modality fusion, and demonstrates outperformance over previous methods in text-to-motion, speech-to-gesture, and music-to-dance tasks.

Whole-body multi-modal human motion generation poses two primary challenges: creating an effective motion generation mechanism and integrating various modalities, such as text, speech, and music, into a cohesive framework. Unlike previous methods that usually employ discrete masked modeling or autoregressive modeling, we develop a continuous masked autoregressive motion transformer, where a causal attention is performed considering the sequential nature within the human motion. Within this transformer, we introduce a gated linear attention and an RMSNorm module, which drive the transformer to pay attention to the key actions and suppress the instability caused by either the abnormal movements or the heterogeneous distributions within multi-modalities. To further enhance both the motion generation and the multimodal generalization, we employ the DiT structure to diffuse the conditions from the transformer towards the targets. To fuse different modalities, AdaLN and cross-attention are leveraged to inject the text, speech, and music signals. Experimental results demonstrate that our framework outperforms previous methods across all modalities, including text-to-motion, speech-to-gesture, and music-to-dance. The code of our method will be made public.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes