Pith. sign in

REVIEW 5 cited by

FG-MDM: Towards Zero-Shot Human Motion Generation via ChatGPT-Refined Descriptions

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 2312.02772 v3 pith:JHLHYAUK submitted 2023-12-05 cs.CV

Xu Shi , Wei Yao , Chuanchen Luo , Junran Peng , Hongwen Zhang , Yunlian Sun This is my paper · ORCID
classification cs.CV
keywords descriptionsgenerationhumanmotionfg-mdmfine-grainedzero-shotmodel
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, significant progress has been made in text-based motion generation, enabling the generation of diverse and high-quality human motions that conform to textual descriptions. However, generating motions beyond the distribution of original datasets remains challenging, i.e., zero-shot generation. By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation. Specifically, we first parse previous vague textual annotations into fine-grained descriptions of different body parts by leveraging a large language model. We then use these fine-grained descriptions to guide a transformer-based diffusion model, which further adopts a design of part tokens. FG-MDM can generate human motions beyond the scope of original datasets owing to descriptions that are closer to motion essence. Our experimental results demonstrate the superiority of FG-MDM over previous methods in zero-shot settings. We will release our fine-grained textual annotations for HumanML3D and KIT.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 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. 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.

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

    cs.CV 2024-11 conditional novelty 7.0 of 10

    A masked-autoregressive diffusion model trained on a compact essential-feature latent space claims state-of-the-art text-to-motion generation under a new essential-dimension evaluation protocol.

  4. CASIM: Composite Aware Semantic Injection for Text to Motion Generation

    cs.CV 2025-02 conditional novelty 6.0 of 10

    CASIM replaces fixed-length text embeddings with token-level cross-attention in text-to-motion models, improving alignment and quality for both diffusion and autoregressive generators.

  5. KinMo: Kinematic-aware Human Motion Understanding and Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    KinMo adds hierarchical body-part-level text annotations to HumanML3D and shows that progressive text-motion alignment improves retrieval, generation, editing, and trajectory control.

Pith tools