Papers › Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

22 Feb 2024arXiv:2402.14654archive 2025-07-28

Fabien Baradel, Matthieu Armando, Salma Galaaoui, Romain Brégier, Philippe Weinzaepfel, Grégory Rogez, Thomas Lucas

We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D location in the camera coordinate system. Our model detects people by predicting coarse 2D heatmaps of person locations, using features produced by a standard Vision Transformer (ViT) backbone. It then predicts their whole-body pose, shape and 3D location using a new cross-attention module called the Human Prediction Head (HPH), with one query attending to the entire set of features for each detected person. As direct prediction of fine-grained hands and facial poses in a single shot, i.e., without relying on explicit crops around body parts, is hard to learn from existing data, we introduce CUFFS, the Close-Up Frames of Full-Body Subjects dataset, containing humans close to the camera with diverse hand poses. We show that incorporating it into the training data further enhances predictions, particularly for hands. Multi-HMR also optionally accounts for camera intrinsics, if available, by encoding camera ray directions for each image token. This simple design achieves strong performance on whole-body and body-only benchmarks simultaneously: a ViT-S backbone on 448×448 images already yields a fast and competitive model, while larger models and higher resolutions obtain state-of-the-art results.

PaperPDFCodeCode 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="2402.14654")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · fixture could not drive it; 7 ran with no contract checked.

By repository: official repository: 9 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.

naver/multi-hmr officialmentioned in papermentioned on GitHubpytorchNOASSERTION 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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has 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 · fixture could not drive it
7ran
1unverified

Licence: 9 of the 9 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 naver/multi-hmr. “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.

apply_threshold naver/multi-hmr/model.py official repository ran licence not identified · pointer only · b07bcabeed382b31 · report
collate_fn naver/multi-hmr/datasets/bedlam.py official repository ran licence not identified · pointer only · 375367e492cbc82c · report
default naver/multi-hmr/blocks/cross_attn_transformer.py official repository ran fingerprinted licence not identified · pointer only · 997f3c08b27aff75 · report
exists naver/multi-hmr/blocks/cross_attn_transformer.py official repository ran licence not identified · pointer only · 7fb8dc7353765ef3 · report
get_1d_sincos_pos_embed_from_grid naver/multi-hmr/multi_hmr_anny/pos_embed.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 4bdd36eab04c3f62 · report
get_2d_sincos_pos_embed naver/multi-hmr/multi_hmr_anny/pos_embed.py official repository ran licence not identified · pointer only · 5458750ed2d5de75 · report
normalization_layer naver/multi-hmr/blocks/cross_attn_transformer.py official repository ran licence not identified · pointer only · 5b283ec09fbc33b7 · report
regression_mlp naver/multi-hmr/model.py official repository ran licence not identified · pointer only · d1957b25490ffc3e · report
get_2d_sincos_pos_embed_from_grid naver/multi-hmr/multi_hmr_anny/pos_embed.py official repository unverified no licence file found · pointer only · 4fd80de79832745d · report

Tasks

3D Human Pose Estimation3D Human Reconstruction3D Multi-Person Mesh Recovery3D Multi-Person Pose EstimationHuman Mesh Recovery

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation UBody Multi-HMR PA-PVE-All 23.6 #1 of 4 Archive leaderboard report
3D Human Pose Estimation UBody Multi-HMR PA-PVE-Face 1.8 #1 of 4 Archive leaderboard report
3D Human Pose Estimation UBody Multi-HMR PA-PVE-Hands 7.0 #1 of 4 Archive leaderboard report
3D Human Pose Estimation UBody Multi-HMR PVE-All 56.4 #1 of 4 Archive leaderboard report
3D Human Pose Estimation UBody Multi-HMR PVE-Face 19.3 #1 of 4 Archive leaderboard report
3D Human Pose Estimation UBody Multi-HMR PVE-Hands 24.9 #1 of 4 Archive leaderboard report
3D Human Reconstruction EHF Multi-HMR MPVPE 44.2 #1 of 3 Archive leaderboard report
3D Human Reconstruction EHF Multi-HMR PA V2V (mm), face 5.5 #1 of 3 Archive leaderboard report
3D Human Reconstruction EHF Multi-HMR PA V2V (mm), whole body 32.7 #1 of 3 Archive leaderboard report
3D Multi-Person Mesh Recovery AGORA Multi-HMR FB-MVE 95.9 #2 of 7 Archive leaderboard report
3D Multi-Person Mesh Recovery AGORA Multi-HMR FB-NMVE 102.0 #2 of 7 Archive leaderboard report
3D Multi-Person Pose Estimation MuPoTS-3D Multi-HMR 3DPCK 89.5 #2 of 10 Archive leaderboard report
Human Mesh Recovery BEDLAM Multi-HMR PVE-All 76.80 #1 of 3 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 EncodingsAdamAttentionBPEConcatenated Skip ConnectionDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSETSoftmaxTransformerVision Transformer

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