OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression

• URL: http://arxiv.org/abs/2510.14954v1
• Date: Thu, 16 Oct 2025 17:57:53 GMT
• Title: OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
• Authors: Zhe Li, Weihao Yuan, Weichao Shen, Siyu Zhu, Zilong Dong, Chang Xu,
• Abstract summary: Whole-body multi-modal human motion generation poses two primary challenges.<n>We create an effective motion generation mechanism and integrate various modalities, such as text, speech, and music, into a cohesive framework.<n>Our framework outperforms previous methods across all modalities, including text-to-motion, speech-to-gesture, and music-to-dance.
• Score: 30.795106931727158
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• OmniMotion-X: Versatile Multimodal Whole-Body Motion Generation [52.579531290307926]
  This paper introduces OmniMotion-X, a versatile framework for whole-body human motion generation.<n> OmniMotion-X efficiently supports diverse multimodal tasks, including text-to-motion, music-to-dance, speech-to-gesture.<n>To enable high-quality multimodal training, we construct OmniMoCap-X, the largest unified multimodal motion dataset to date.
  arXiv  Detail & Related papers  (2025-10-22T17:25:33Z)
• MotionVerse: A Unified Multimodal Framework for Motion Comprehension, Generation and Editing [53.98607267063729]
  MotionVerse is a framework to comprehend, generate, and edit human motion in both single-person and multi-person scenarios.<n>We employ a motion tokenizer with residual quantization, which converts continuous motion sequences into multi-stream discrete tokens.<n>We also introduce a textitDelay Parallel Modeling strategy, which temporally staggers the encoding of residual token streams.
  arXiv  Detail & Related papers  (2025-09-28T04:20:56Z)
• GENMO: A GENeralist Model for Human MOtion [64.16188966024542]
  We present GENMO, a unified Generalist Model for Human Motion that bridges motion estimation and generation in a single framework.<n>Our key insight is to reformulate motion estimation as constrained motion generation, where the output motion must precisely satisfy observed conditioning signals.<n>Our novel architecture handles variable-length motions and mixed multimodal conditions (text, audio, video) at different time intervals, offering flexible control.
  arXiv  Detail & Related papers  (2025-05-02T17:59:55Z)
• Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy [73.75271615101754]
  We present Dita, a scalable framework that leverages Transformer architectures to directly denoise continuous action sequences.<n>Dita employs in-context conditioning -- enabling fine-grained alignment between denoised actions and raw visual tokens from historical observations.<n>Dita effectively integrates cross-embodiment datasets across diverse camera perspectives, observation scenes, tasks, and action spaces.
  arXiv  Detail & Related papers  (2025-03-25T15:19:56Z)
• Dynamic Motion Synthesis: Masked Audio-Text Conditioned Spatio-Temporal Transformers [13.665279127648658]
  This research presents a novel motion generation framework designed to produce whole-body motion sequences conditioned on multiple modalities simultaneously. By integrating spatial attention mechanisms and a token critic we ensure consistency and naturalness in the generated motions.
  arXiv  Detail & Related papers  (2024-09-03T04:19:27Z)
• MotionCraft: Crafting Whole-Body Motion with Plug-and-Play Multimodal Controls [30.487510829107908]
  We propose MotionCraft, a unified diffusion transformer that crafts whole-body motion with plug-and-play multimodal control. Our framework employs a coarse-to-fine training strategy, starting with the first stage of text-to-motion semantic pre-training. We introduce MC-Bench, the first available multimodal whole-body motion generation benchmark based on the unified SMPL-X format.
  arXiv  Detail & Related papers  (2024-07-30T18:57:06Z)
• DiverseMotion: Towards Diverse Human Motion Generation via Discrete Diffusion [70.33381660741861]
  We present DiverseMotion, a new approach for synthesizing high-quality human motions conditioned on textual descriptions. We show that our DiverseMotion achieves the state-of-the-art motion quality and competitive motion diversity.
  arXiv  Detail & Related papers  (2023-09-04T05:43:48Z)
• Priority-Centric Human Motion Generation in Discrete Latent Space [59.401128190423535]
  We introduce a Priority-Centric Motion Discrete Diffusion Model (M2DM) for text-to-motion generation. M2DM incorporates a global self-attention mechanism and a regularization term to counteract code collapse. We also present a motion discrete diffusion model that employs an innovative noise schedule, determined by the significance of each motion token.
  arXiv  Detail & Related papers  (2023-08-28T10:40:16Z)
• Interactive Character Control with Auto-Regressive Motion Diffusion Models [18.727066177880708]
  We propose A-MDM (Auto-regressive Motion Diffusion Model) for real-time motion synthesis. Our conditional diffusion model takes an initial pose as input, and auto-regressively generates successive motion frames conditioned on previous frame. We introduce a suite of techniques for incorporating interactive controls into A-MDM, such as task-oriented sampling, in-painting, and hierarchical reinforcement learning.
  arXiv  Detail & Related papers  (2023-06-01T07:48:34Z)
• ActFormer: A GAN Transformer Framework towards General Action-Conditioned 3D Human Motion Generation [16.1094669439815]
  We present a GAN Transformer framework for general action-conditioned 3D human motion generation. Our approach consists of a powerful Action-conditioned transFormer (ActFormer) under a GAN training scheme. ActFormer can be naturally extended to multi-person motions by alternately modeling temporal correlations and human interactions with Transformer encoders.
  arXiv  Detail & Related papers  (2022-03-15T07:50:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.