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 page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 1 code sample harvested from 1 repository linked to this paper: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 1 sample from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No date is recorded for the sample that ran: its level was written before Syntology's graph kept the date.

guytevet/motion-diffusion-model officialmentioned in papermentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified 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 (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is 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.

Harvested from guytevet/motion-diffusion-model. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

guytevet/motion-diffusion-model official repository 1 sample, 1 ran (1 instrument-failed) · 0 unverified
construct_template_variables in 6 papers sample/generate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · fe28ada12e5b4764 · report fixture: signature unconstrained:bool/0/bool · returned tuple · level recorded, date not recorded

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