Papers › MoMask: Generative Masked Modeling of 3D Human Motions

MoMask: Generative Masked Modeling of 3D Human Motions

29 Nov 2023CVPR 2024 1arXiv:2312.00063archive 2025-07-28

Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed, Sen Wang, Li Cheng

We introduce MoMask, a novel masked modeling framework for text-driven 3D human motion generation. In MoMask, a hierarchical quantization scheme is employed to represent human motion as multi-layer discrete motion tokens with high-fidelity details. Starting at the base layer, with a sequence of motion tokens obtained by vector quantization, the residual tokens of increasing orders are derived and stored at the subsequent layers of the hierarchy. This is consequently followed by two distinct bidirectional transformers. For the base-layer motion tokens, a Masked Transformer is designated to predict randomly masked motion tokens conditioned on text input at training stage. During generation (i.e. inference) stage, starting from an empty sequence, our Masked Transformer iteratively fills up the missing tokens; Subsequently, a Residual Transformer learns to progressively predict the next-layer tokens based on the results from current layer. Extensive experiments demonstrate that MoMask outperforms the state-of-art methods on the text-to-motion generation task, with an FID of 0.045 (vs e.g. 0.141 of T2M-GPT) on the HumanML3D dataset, and 0.228 (vs 0.514) on KIT-ML, respectively. MoMask can also be seamlessly applied in related tasks without further model fine-tuning, such as text-guided temporal inpainting.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology 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="2312.00063")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

EricGuo5513/momask-codes officialmentioned 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

11 samples harvested; 8 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
7ran
3unverified

Licence: 0 of the 11 samples are 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 EricGuo5513/momask-codes. “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.

get_pad_mask_idx EricGuo5513/momask-codes/models/mask_transformer/tools.py official repository ran MIT (permissive) · b3a8c0636cb0b673 · report
get_padding_mask EricGuo5513/momask-codes/models/t2m_eval_modules.py official repository ran MIT (permissive) · 5fdf5df48906cb4f · report
get_subsequent_mask EricGuo5513/momask-codes/models/mask_transformer/tools.py official repository ran MIT (permissive) · fb6fcde255d6bf72 · report
positional_encoding EricGuo5513/momask-codes/models/t2m_eval_modules.py official repository ran MIT (permissive) · cdd18b1ca5a038e1 · report
qinv EricGuo5513/momask-codes/common/quaternion.py official repository ran fingerprinted MIT (permissive) · 9593fec6c1bf25e7 · report
qinv_np EricGuo5513/momask-codes/common/quaternion.py official repository ran fingerprinted MIT (permissive) · 66024edafa8c53fb · report
qnormalize EricGuo5513/momask-codes/common/quaternion.py official repository ran fingerprinted MIT (permissive) · bac0877915201be1 · report
top_k_logits EricGuo5513/momask-codes/models/t2m_eval_modules.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f0021cdea13e4da · report
build_evaluators EricGuo5513/momask-codes/models/t2m_eval_wrapper.py official repository unverified MIT (permissive) · 939b4a7d3178c666 · report
build_models EricGuo5513/momask-codes/models/t2m_eval_wrapper.py official repository unverified MIT (permissive) · 0e89c3d7e91130b0 · report
lengths_to_mask EricGuo5513/momask-codes/models/mask_transformer/tools.py official repository unverified MIT (permissive) · 80c46a6e9bfa68f7 · report

Tasks

Human motion predictionMotion ForecastingMotion GenerationMotion InterpolationMotion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis HumanML3D MoMask FID 0.045 #5 of 37 Archive leaderboard report
Motion Synthesis HumanML3D MoMask Multimodality 1.241 #5 of 37 Archive leaderboard report
Motion Synthesis HumanML3D MoMask R Precision Top3 0.807 #5 of 37 Archive leaderboard report
Motion Synthesis KIT Motion-Language MoMask FID 0.204 #8 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language MoMask Multimodality 1.131 #8 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language MoMask R Precision Top3 0.781 #8 of 31 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

Absolute Position EncodingsAdamAttentionBASEBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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