Papers › Human Motion Diffusion Model

Human Motion Diffusion Model

29 Sep 2022arXiv:2209.14916archive 2025-07-28

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

Natural and expressive human motion generation is the holy grail of computer animation. It is a challenging task, due to the diversity of possible motion, human perceptual sensitivity to it, and the difficulty of accurately describing it. Therefore, current generative solutions are either low-quality or limited in expressiveness. Diffusion models, which have already shown remarkable generative capabilities in other domains, are promising candidates for human motion due to their many-to-many nature, but they tend to be resource hungry and hard to control. In this paper, we introduce Motion Diffusion Model (MDM), a carefully adapted classifier-free diffusion-based generative model for the human motion domain. MDM is transformer-based, combining insights from motion generation literature. A notable design-choice is the prediction of the sample, rather than the noise, in each diffusion step. This facilitates the use of established geometric losses on the locations and velocities of the motion, such as the foot contact loss. As we demonstrate, 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. https://guytevet.github.io/mdm-page/ .

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2209.14916")

Code

Syntology Ran 1 of 1 code samples harvested from 0 repositories linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

guytevet/motion-diffusion-model officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong

Licence: 1 of the 1 sample is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

construct_template_variables identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · fe28ada12e5b4764 · report

Tasks

3D GenerationMotion GenerationMotion Synthesismodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Generation E.T. the Exceptional Trajectories MDM ClaTr-Score 18.32 #4 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories MDM Classifier-F1 0.34 #4 of 4 Archive leaderboard report
3D Generation E.T. the Exceptional Trajectories MDM FD_ClaTr 6.79 #4 of 4 Archive leaderboard report
Motion Synthesis HumanAct12 MDM Accuracy 0.99 #1 of 2 Archive leaderboard report
Motion Synthesis HumanAct12 MDM FID 0.08 #1 of 2 Archive leaderboard report
Motion Synthesis HumanAct12 MDM Multimodality 2.58 #1 of 2 Archive leaderboard report
Motion Synthesis HumanML3D MDM Diversity 9.559 #29 of 37 Archive leaderboard report
Motion Synthesis HumanML3D MDM FID 0.544 #29 of 37 Archive leaderboard report
Motion Synthesis HumanML3D MDM Multimodality 2.799 #29 of 37 Archive leaderboard report
Motion Synthesis HumanML3D MDM R Precision Top3 0.611 #29 of 37 Archive leaderboard report
Motion Synthesis Inter-X MDM FID 23.701 #4 of 6 Archive leaderboard report
Motion Synthesis Inter-X MDM MMDist 9.548 #4 of 6 Archive leaderboard report
Motion Synthesis Inter-X MDM MModality 3.490 #4 of 6 Archive leaderboard report
Motion Synthesis Inter-X MDM R-Precision Top3 0.426 #4 of 6 Archive leaderboard report
Motion Synthesis InterHuman MDM FID 9.167 #8 of 10 Archive leaderboard report
Motion Synthesis InterHuman MDM MMDist 7.125 #8 of 10 Archive leaderboard report
Motion Synthesis InterHuman MDM MModality 2.35 #8 of 10 Archive leaderboard report
Motion Synthesis InterHuman MDM R-Precision Top3 0.339 #8 of 10 Archive leaderboard report
Motion Synthesis KIT Motion-Language MDM Diversity 10.847 #20 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language MDM FID 0.497 #20 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language MDM Multimodality 1.907 #20 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language MDM R Precision Top3 0.396 #20 of 31 Archive leaderboard report
Motion Synthesis Motion-X MDM Diversity 11.400 #4 of 4 Archive leaderboard report
Motion Synthesis Motion-X MDM FID 3.800 #4 of 4 Archive leaderboard report
Motion Synthesis Motion-X MDM MModality 2.530 #4 of 4 Archive leaderboard report
Motion Synthesis Motion-X MDM TMR-Matching Score 0.840 #4 of 4 Archive leaderboard report
Motion Synthesis Motion-X MDM TMR-R-Precision Top3 0.6341 #4 of 4 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections