2026-05-27原文

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

RoMo is a large-scale, high-quality human motion dataset that addresses the trade-off between small mocap datasets and large low-quality in-the-wild collections. It uses a taxonomy-aware filtering pipeline, a three-level semantic taxonomy for annotation, and a fine-grained evaluation framework. Models trained on RoMo achieve state-of-the-art fidelity and diversity, and the accompanying Motion Toolbox standardizes metrics and data conversion.

Article intelligence

InvestorsAdvanced

Key points

RoMo bridges the gap between small high-fidelity mocap datasets and large low-quality in-the-wild data
A taxonomy-aware filtering pipeline removes static and artifact-prone sequences
A three-level semantic taxonomy enables fine-grained per-category evaluation
Models trained on RoMo show superior understanding of complex text prompts

Why it matters

This matters because roMo bridges the gap between small high-fidelity mocap datasets and large low-quality in-the-wild data.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.26241] RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation

[Submitted on 25 May 2026]

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

View a PDF of the paper titled RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation, by Jiahao Zhang and 11 other authors

View PDF HTML (experimental)

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.

Comments: Accepted to CVPR'26

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2605.26241 [cs.CV]

(or arXiv:2605.26241v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.26241

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jiahao Zhang [view email] [v1] Mon, 25 May 2026 18:07:18 UTC (6,825 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation, by Jiahao Zhang and 11 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)