The reviewed record of science sign in
Pith

arxiv: 2501.05098 · v1 · pith:GAJ57S6R · submitted 2025-01-09 · cs.CV

Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:GAJ57S6Rrecord.jsonopen to challenge →

classification cs.CV
keywords motionwhole-bodymotion-xhumanannotationdatasetdescriptionslabels
0
0 comments X
read the original abstract

In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lacking facial expressions, hand gestures, and fine-grained pose descriptions, and are typically limited to lab settings with manually labeled text descriptions, thereby restricting their scalability. To address this issue, we develop a scalable annotation pipeline that can automatically capture 3D whole-body human motion and comprehensive textural labels from RGB videos and build the Motion-X dataset comprising 81.1K text-motion pairs. Furthermore, we extend Motion-X into Motion-X++ by improving the annotation pipeline, introducing more data modalities, and scaling up the data quantities. Motion-X++ provides 19.5M 3D whole-body pose annotations covering 120.5K motion sequences from massive scenes, 80.8K RGB videos, 45.3K audios, 19.5M frame-level whole-body pose descriptions, and 120.5K sequence-level semantic labels. Comprehensive experiments validate the accuracy of our annotation pipeline and highlight Motion-X++'s significant benefits for generating expressive, precise, and natural motion with paired multimodal labels supporting several downstream tasks, including text-driven whole-body motion generation,audio-driven motion generation, 3D whole-body human mesh recovery, and 2D whole-body keypoints estimation, etc.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation

    cs.CV 2026-06 unverdicted novelty 7.0

    A two-stage generative model (Graph CVAE + flow matching) learns topology-agnostic motion codes from a new 5k-topology dataset and retargets video motion to arbitrary unseen skeletons.

  2. GUSH3R: Everyone Everywhere All at Once as Gaussians

    cs.CV 2026-07 conditional novelty 6.0

    A feed-forward framework predicts unified 3D Gaussian representations of dynamic humans and static scenes from monocular video in a single forward pass.

  3. In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis from Language Models to Physics

    cs.RO 2026-06 unverdicted novelty 6.0

    ICMPG combines LLM-based candidate generation with MPC-style physical simulation and semantic scoring to produce text-driven human motions that are both plausible and faithful.

  4. LIMMT: Less is More for Motion Tracking

    cs.RO 2026-06 unverdicted novelty 6.0

    A data-centric approach shows that less than 3% of AMASS motion data, filtered by physics feasibility, diversity, and complexity, yields better humanoid tracking policies than the full dataset.

  5. AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling

    cs.CV 2026-05 unverdicted novelty 6.0

    AnyMo is a masked-modeling framework for any-modality human motion generation trained on the new OmniHuMo dataset of 5,000+ hours of multimodal motion sequences.

  6. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control

    cs.GR 2026-05 unverdicted novelty 6.0

    SCRIPT presents a scalable diffusion policy with JAST-DiT architecture, nonlinear history conditioning, and RLHR post-training that claims to outperform prior methods on text alignment, motion quality, and physical re...

  7. SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control

    cs.GR 2026-05 unverdicted novelty 6.0

    A new diffusion transformer policy with joint attention over actions, states, and text plus RL post-training outperforms prior methods on language alignment and motion quality for humanoid control.

  8. HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluation

    cs.CV 2026-04 unverdicted novelty 6.0

    HuM-Eval evaluates human motion videos with a coarse-to-fine approach using VLM global checks plus 2D pose and 3D motion analysis, reaching 58.2% average correlation with human judgments and introducing a 1000-prompt ...

  9. Beyond MoCap: Scaling Motion Tokenizers with Synthetic Human Motion for Generative Modeling

    cs.CV 2026-06 unverdicted novelty 5.0

    Scaling both synthetic motion data volume and VQ-VAE codebook size yields richer motion vocabularies and measurable gains on standard generation benchmarks.

  10. OMG: Omni-Modal Motion Generation for Generalist Humanoid Control

    cs.RO 2026-06 unverdicted novelty 5.0

    OMG is a diffusion model for omni-modal whole-body humanoid motion generation that uses language, audio, and reference motions after large-scale data curation to achieve state-of-the-art performance and adaptation.

  11. Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

    cs.RO 2026-06 unverdicted novelty 5.0

    Humanoid-GPT is a causal Transformer pre-trained on a unified billion-scale motion dataset that tracks dynamic behaviors with zero-shot generalization to unseen motions and tasks.

  12. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 5.0

    The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.

  13. Fine-grained Human Motion Understanding with Language Models

    cs.CV 2026-06 unverdicted novelty 4.0

    LLM model using explicit timestamped skeletal pose sequences and diverse pose/motion supervision achieves SOTA on multiple motion understanding benchmarks, including with 2D input surpassing prior 3D methods.

  14. From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation

    cs.GR 2026-04 unverdicted novelty 4.0

    The paper surveys 3D content generation literature using a taxonomy of asset types and production stages to evaluate progress toward engine-ready assets.