Pith Number

pith:6RR77ZAE

pith:2022:6RR77ZAEQNDTA6NHRWFXDKZQLO

not attested not anchored not stored refs resolved

Human Motion Diffusion Model

Amit H. Bermano, Brian Gordon, Daniel Cohen-Or, Guy Tevet, Sigal Raab, Yonatan Shafir

A diffusion model for human motion generates natural sequences from text or actions by predicting the clean sample at each step instead of noise.

arxiv:2209.14916 v2 · 2022-09-29 · cs.CV · cs.GR

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{6RR77ZAEQNDTA6NHRWFXDKZQLO}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

MDM is a generic approach, enabling different modes of conditioning, and different generation tasks. We show that our model is trained with lightweight resources and yet achieves state-of-the-art results on leading benchmarks for text-to-motion and action-to-motion.

C2weakest assumption

That predicting the clean sample (instead of noise) at each diffusion step, combined with geometric losses, will reliably produce higher-quality and more controllable motions than standard noise-prediction diffusion on the chosen motion datasets and benchmarks.

C3one line summary

MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.

References

20 extracted · 20 resolved · 9 Pith anchors

[1] Accessed: 2021-12-25 2021

[2] A spatio-temporal transformer for 3d human motion prediction 2021

[3] Text2gestures: A transformer-based network for generating emotive body ges- tures for virtual agents 2021

[4] Implicit neural representations for variable length human motion generation

[5] Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation · arXiv:1406.1078

Formal links

2 machine-checked theorem links

Cited by

37 papers in Pith

Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes

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

MARRS: Masked Autoregressive Unit-based Reaction Synthesis

SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control

Toward Seamless Physical Human-Humanoid Interaction: Insights from Control, Intent, and Modeling with a Vision for What Comes Next

Receipt and verification

First computed	2026-05-17T23:38:53.689359Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e

Aliases

arxiv: 2209.14916 · arxiv_version: 2209.14916v2 · doi: 10.48550/arxiv.2209.14916 · pith_short_12: 6RR77ZAEQNDT · pith_short_16: 6RR77ZAEQNDTA6NH · pith_short_8: 6RR77ZAE

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/6RR77ZAEQNDTA6NHRWFXDKZQLO \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: f463ffe40483473079a78d8b71ab305bae8a203260994b38e86798372542e20e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c0b9c2d8fc337f851c239bf0ba9d09df604c3ab48c8c6b4fd7eb3b3770ba84a9",
    "cross_cats_sorted": [
      "cs.GR"
    ],
    "license": "http://creativecommons.org/licenses/by-sa/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2022-09-29T16:27:53Z",
    "title_canon_sha256": "35607a551d789646ae0f20afbde072ed395b8824a618a0b36b1e2614f96b35d7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2209.14916",
    "kind": "arxiv",
    "version": 2
  }
}