Pith. sign in

REVIEW 11 cited by

Rethinking Diffusion for Text-Driven Human Motion Generation: Redundant Representations, Evaluation, and Masked Autoregression

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2411.16575 v2 pith:TYYJGRV3 submitted 2024-11-25 cs.CV

Zichong Meng , Yiming Xie , Xiaogang Peng , Zeyu Han , Huaizu Jiang This is my paper · ORCID
classification cs.CV
keywords generationmethodsmotiondiffusion-basedhumancontinuousdatalimitations
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Since 2023, Vector Quantization (VQ)-based discrete generation methods have rapidly dominated human motion generation, primarily surpassing diffusion-based continuous generation methods in standard performance metrics. However, VQ-based methods have inherent limitations. Representing continuous motion data as limited discrete tokens leads to inevitable information loss, reduces the diversity of generated motions, and restricts their ability to function effectively as motion priors or generation guidance. In contrast, the continuous space generation nature of diffusion-based methods makes them well-suited to address these limitations and with even potential for model scalability. In this work, we systematically investigate why current VQ-based methods perform well and explore the limitations of existing diffusion-based methods from the perspective of motion data representation and distribution. Drawing on these insights, we preserve the inherent strengths of a diffusion-based human motion generation model and gradually optimize it with inspiration from VQ-based approaches. Our approach introduces a human motion diffusion model enabled to perform masked autoregression, optimized with a reformed data representation and distribution. Additionally, we propose a more robust evaluation method to assess different approaches. Extensive experiments on various datasets demonstrate our method outperforms previous methods and achieves state-of-the-art performances.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

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

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

    cs.CV 2026-07 conditional novelty 7.0 of 10

    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 of 10

    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. MDD: A Dataset for Text-and-Music Conditioned Duet Dance Generation

    cs.GR 2025-08 conditional novelty 7.0 of 10

    MDD is the first dataset to pair text, music, and 3D duet dance motion, enabling two new text-conditioned duet generation tasks.

  4. Absolute Coordinates Make Motion Generation Easy

    cs.CV 2025-05 conditional novelty 7.0 of 10

    Using absolute 3D joint coordinates with a plain Transformer and velocity-prediction diffusion outperforms the standard local-relative motion representation, improving fidelity and enabling direct control.

  5. Next-Scale Autoregressive Models for Text-to-Motion Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    Next-scale autoregressive modeling with cross-scale and in-scale refinements produces SOTA text-to-motion generation by enforcing coarse-to-fine causal hierarchy.

  6. MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A semantically aligned latent space plus multi-token cross-attention conditioning sets a new state of the art in text-to-human-motion generation on HumanML3D.

  7. IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation

    cs.CV 2025-12 conditional novelty 6.0 of 10

    Interleaving motion generation with text-motion assessment and refinement improves alignment between generated human motion and goal text.

  8. Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A 7B text-to-motion model trained on the new 2M-clip MotionMillion dataset is reported to generalize zero-shot to complex, out-of-domain prompts.

  9. PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A text-to-motion pipeline that projects motions through physics-based imitation for training and post-processing, plus new consistency and marker-interaction losses.

  10. ANT: Adaptive Neural Temporal-Aware Text-to-Motion Model

    cs.CV 2025-06 conditional novelty 5.0 of 10

    ANT makes text embeddings change across denoising steps and schedules classifier-free guidance to decay, improving text-motion alignment in diffusion text-to-motion models.

  11. Motion Generation: A Survey of Generative Approaches and Benchmarks

    cs.CV 2025-07 unverdicted novelty 3.0 of 10

    A structured survey that categorizes recent motion generation methods by underlying generative approach and compiles datasets, metrics, and statistical trends.

Pith tools