Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion

• URL: http://arxiv.org/abs/2606.21135v1
• Date: Fri, 19 Jun 2026 06:19:29 GMT
• Title: Odoriko: A Shape-Aware Multimodal Diffusion Framework for Human Motion
• Abstract summary: Odoriko is the first unified multimodal motion generation framework.<n>It reflects subject bio-morphological information directly in synthesized motion output.<n>It recovers subject morphology alongside motion, unifying estimation and generation in one framework.
• Score: 40.9326670703426
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Human motion generation has been widely studied across diverse input modalities, text, music, and video, and recent efforts have unified these into single multimodal frameworks. However, while morphological factors such as gender and body shape are known to produce distinct kinematic signatures, no existing unified framework incorporates this into generation, treating all subjects as morphologically equivalent. We present Odoriko, the first unified multimodal motion generation framework that reflects subject bio-morphological information directly in synthesized motion output. Rather than averaging over subject variation, Odoriko generates motion that is consistent with who is moving, not just what they are asked to do, across text, music, and video conditions within a single model. When explicit morphological information is unavailable, Odoriko additionally recovers subject morphology alongside motion, unifying estimation and generation in one framework. Extensive experiments across text-to-motion, music-to-dance, and video-to-motion benchmarks demonstrate that Odoriko matches or exceeds prior specialized models on standard metrics, while enabling morphology-consistent generation that no existing unified framework supports.

Related papers

• IAM: Identity-Aware Human Motion and Shape Joint Generation [14.037850965399384]
  We propose an identity-aware motion generation framework that explicitly models the relationship between body morphology and motion dynamics.<n>We introduce a joint motion-shape generation paradigm that simultaneously synthesizes motion sequences and body shape parameters.<n>Experiments on motion capture datasets and large-scale in-the-wild videos demonstrate improved motion realism and motion-identity consistency.
  arXiv  Detail & Related papers  (2026-04-28T03:15:12Z)
• Training-free Motion Factorization for Compositional Video Generation [57.819757612370374]
  We propose a motion factorization framework that decomposes complex motion into three primary categories: motionlessness, rigid motion, and non-rigid motion.<n>Our framework achieves impressive performance in motion synthesis on real-world benchmarks.
  arXiv  Detail & Related papers  (2026-03-10T02:27:48Z)
• Topology-Agnostic Animal Motion Generation from Text Prompt [16.557163253248817]
  We introduce OmniZoo, a large-scale animal motion dataset spanning 140 species and 32,979 sequences.<n>We propose a generalized autoregressive motion generation framework capable of producing text-driven motions for arbitrary skeletal topologies.
  arXiv  Detail & Related papers  (2025-12-11T07:08:29Z)
• X-MoGen: Unified Motion Generation across Humans and Animals [9.967329240441844]
  X-MoGen is the first unified framework for cross-species text-driven motion generation covering both humans and animals.<n>We construct textbfUniMo4D, 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.<n>Experiments on UniMo4D demonstrate that X-MoGen outperforms state-of-the-art methods on both seen and unseen species.
  arXiv  Detail & Related papers  (2025-08-07T08:51:51Z)
• SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation [56.90807453045657]
  SynMotion is a motion-customized video generation model that jointly leverages semantic guidance and visual adaptation.<n>At the semantic level, we introduce the dual-em semantic comprehension mechanism which disentangles subject and motion representations.<n>At the visual level, we integrate efficient motion adapters into a pre-trained video generation model to enhance motion fidelity and temporal coherence.
  arXiv  Detail & Related papers  (2025-06-30T10:09:32Z)
• 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)
• MoDi: Unconditional Motion Synthesis from Diverse Data [51.676055380546494]
  We present MoDi, an unconditional generative model that synthesizes diverse motions. Our model is trained in a completely unsupervised setting from a diverse, unstructured and unlabeled motion dataset. We show that despite the lack of any structure in the dataset, the latent space can be semantically clustered.
  arXiv  Detail & Related papers  (2022-06-16T09:06:25Z)
• GANimator: Neural Motion Synthesis from a Single Sequence [38.361579401046875]
  We present GANimator, a generative model that learns to synthesize novel motions from a single, short motion sequence. GANimator generates motions that resemble the core elements of the original motion, while simultaneously synthesizing novel and diverse movements. We show a number of applications, including crowd simulation, key-frame editing, style transfer, and interactive control, which all learn from a single input sequence.
  arXiv  Detail & Related papers  (2022-05-05T13:04:14Z)
• Hierarchical Style-based Networks for Motion Synthesis [150.226137503563]
  We propose a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by decomposing a long-range generation task in a hierarchical manner. On large-scale skeleton dataset, we show that the proposed method is able to synthesise long-range, diverse and plausible motion.
  arXiv  Detail & Related papers  (2020-08-24T02:11:02Z)

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.