Pith. sign in

REVIEW 9 cited by

T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.06052 v4 pith:XSSBR3XI submitted 2023-01-15 cs.CV

T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations

classification cs.CV
keywords motionhumansimplevq-vaeapproachapproachescompetitivedataset
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation

    cs.CV 2026-07 conditional novelty 7.0

    Distilling frozen Motion-JEPA features into a compact 32-D latent whose geometry is coupled to the decoder lets a standard non-autoregressive flow-matching DiT reach state-of-the-art text-to-motion quality on HumanML3...

  2. ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation

    cs.CV 2026-05 unverdicted novelty 7.0

    ScaleMoGen introduces a scale-wise autoregressive framework that quantizes motions into hierarchical discrete tokens and predicts next-scale maps to achieve SOTA FID 0.030 on HumanML3D and text-guided editing.

  3. ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation

    cs.CV 2026-05 conditional novelty 7.0

    ScaleMoGen applies next-scale autoregressive prediction to human motion generation with multi-scale skeletal-temporal bitwise token maps, reporting SOTA FID on HumanML3D.

  4. SDFlow: Similarity-Driven Flow Matching for Time Series Generation

    cs.AI 2026-05 unverdicted novelty 7.0

    SDFlow uses similarity-driven flow matching with low-rank manifold decomposition and a categorical posterior to generate high-fidelity long time series in VQ space without step-wise error accumulation.

  5. ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos

    cs.CV 2026-04 unverdicted novelty 7.0

    ExpertEdit edits novice motions to expert skill levels by learning a motion prior from unpaired videos and infilling masked skill-critical spans.

  6. 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.

  7. SDFlow: Similarity-Driven Flow Matching for Time Series Generation

    cs.AI 2026-05 unverdicted novelty 6.0

    SDFlow learns a global transport map via similarity-driven flow matching in VQ latent space, using low-rank manifold decomposition and a categorical posterior to handle discreteness, yielding SOTA long-horizon perform...

  8. MSDformer: Multi-scale Discrete Transformer For Time Series Generation

    cs.LG 2025-05 unverdicted novelty 5.0

    MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-...

  9. Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos

    cs.CV 2026-05 unverdicted novelty 4.0

    HTD-Refine uses a temporal transformer (PVA-Net) to predict high-order dynamics and refines HMR outputs via optimization for more natural motion.