RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation

• URL: http://arxiv.org/abs/2605.26241v1
• Date: Mon, 25 May 2026 18:07:18 GMT
• Title: RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation
• Abstract summary: RoMo is a rich, large-scale, carefully curated dataset of in-the-wild human motions.<n>Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy.<n>We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts.
• Score: 39.180328728133496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, however, has lagged behind, constrained by an unsatisfying choice between small, high-fidelity motion capture datasets and large-scale in-the-wild collections dominated by static or low-quality sequences. We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs. To ensure quality, we introduce a taxonomy-aware filtering pipeline that aggressively removes static and artifact-prone sequences. Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy. This hierarchical structure enables fine-grained, per-category evaluation, that reveals model strengths and weaknesses obscured by global metrics. We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts. Finally, we release the Motion Toolbox to standardize metrics, data conversion, and visualization, establishing a foundation for reproducible and interpretable motion generation research.

Related papers

• MotionDreamer: Universal Skeletal Motion Generation for 3D Rigged Shapes [52.45449797329548]
  MotionDreamer is a diffusion-based framework for category-agnostic skeletal animation generation from 2D video guidance.<n>We propose a structural-semantic injection mechanism to bridge the gap between 2D visual motion cues and heterogeneous 3D skeletal structures.<n>Our approach significantly outperforms existing methods, setting a new state-of-the-art benchmark for robust and efficient 4D asset generation.
  arXiv  Detail & Related papers  (2026-06-01T00:42:31Z)
• HandX: Scaling Bimanual Motion and Interaction Generation [55.486397101415]
  HandX is a unified foundation spanning data, annotation, and evaluation.<n>We consolidate and filter existing datasets for quality, and collect a new motion-capture dataset.<n>Experiments demonstrate high-quality dexterous motion generation, supported by our newly proposed hand-focused metrics.
  arXiv  Detail & Related papers  (2026-03-30T17:59:49Z)
• The Quest for Generalizable Motion Generation: Data, Model, and Evaluation [66.57596758773309]
  We present a framework that systematically transfers knowledge from ViGen to MoGen across three key pillars: data, modeling, and evaluation.<n>First, we introduce ViMoGen-228K, a large-scale dataset comprising 228,000 high-quality motion samples.<n>Second, we propose ViMoGen, a flow-matching-based diffusion transformer that unifies priors from MoCap data and ViGen models through gated multimodal conditioning.<n>Third, we present MBench, a hierarchical benchmark designed for fine-grained evaluation across motion quality, prompt fidelity, and generalization ability.
  arXiv  Detail & Related papers  (2025-10-30T17:59:27Z)
• Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations [14.972702558607557]
  We introduce the first standardized benchmark for evaluating multi-factor sequential disentanglement across six diverse datasets.<n>We propose a post-hoc Latent Exploration Stage to automatically align latent dimensions with semantic factors, and introduce a Koopman-inspired model that achieves state-of-the-art results.<n>Our code is available on GitHub, and the datasets and trained models are available on Hugging Face.
  arXiv  Detail & Related papers  (2025-10-20T08:58:23Z)
• How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects [37.10752536568922]
  Motion synthesis for diverse object categories holds great potential for 3D content creation.<n>We address the lack of comprehensive motion datasets that include a wide range of high-quality motions and annotations.<n>We introduce rig augmentation techniques that generate diverse motion data while preserving consistent dynamics.
  arXiv  Detail & Related papers  (2025-03-06T09:39:09Z)
• Scaling Large Motion Models with Million-Level Human Motions [67.40066387326141]
  We present MotionLib, the first million-level dataset for motion generation.<n>We train a large motion model named projname, demonstrating robust performance across a wide range of human activities.
  arXiv  Detail & Related papers  (2024-10-04T10:48:54Z)
• Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance [48.986552871497]
  We introduce a novel two-stage framework that employs scene affordance as an intermediate representation. By leveraging scene affordance maps, our method overcomes the difficulty in generating human motion under multimodal condition signals. Our approach consistently outperforms all baselines on established benchmarks, including HumanML3D and HUMANISE.
  arXiv  Detail & Related papers  (2024-03-26T18:41:07Z)
• 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)

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.