Papers › MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

24 Nov 2021CVPR 2022 1arXiv:2111.12707archive 2025-07-28

Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, Luc van Gool

Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion. Most existing works attempt to solve both issues by exploiting spatial and temporal relationships. However, those works ignore the fact that it is an inverse problem where multiple feasible solutions (i.e., hypotheses) exist. To relieve this limitation, we propose a Multi-Hypothesis Transformer (MHFormer) that learns spatio-temporal representations of multiple plausible pose hypotheses. In order to effectively model multi-hypothesis dependencies and build strong relationships across hypothesis features, the task is decomposed into three stages: (i) Generate multiple initial hypothesis representations; (ii) Model self-hypothesis communication, merge multiple hypotheses into a single converged representation and then partition it into several diverged hypotheses; (iii) Learn cross-hypothesis communication and aggregate the multi-hypothesis features to synthesize the final 3D pose. Through the above processes, the final representation is enhanced and the synthesized pose is much more accurate. Extensive experiments show that MHFormer achieves state-of-the-art results on two challenging datasets: Human3.6M and MPI-INF-3DHP. Without bells and whistles, its performance surpasses the previous best result by a large margin of 3% on Human3.6M. Code and models are available at \url{https://github.com/Vegetebird/MHFormer}.

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="2111.12707")

Code

Syntology Ran 4 of 10 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Vegetebird/MHFormer 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

10 samples harvested; 4 ran; 0 honoured the contract we drafted; 6 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.

4ran
6unverified

Licence: 0 of the 10 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 Vegetebird/MHFormer. “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.

coco_h36m Vegetebird/MHFormer/demo/lib/preprocess.py official repository ran MIT (permissive) · f3a0f7cf8690505f · report
h36m_coco_format Vegetebird/MHFormer/demo/lib/preprocess.py official repository ran MIT (permissive) · 85be84dc21eb6ce3 · report
revise_kpts Vegetebird/MHFormer/demo/lib/preprocess.py official repository ran MIT (permissive) · b9f70678ddc9add2 · report
show2Dpose Vegetebird/MHFormer/demo/vis.py official repository ran MIT (permissive) · 091700eabe2e929a · report
camera_to_world Vegetebird/MHFormer/common/camera.py official repository unverified MIT (permissive) · 0892bc8406224611 · report
deterministic_random Vegetebird/MHFormer/common/utils.py official repository unverified MIT (permissive) · ec58bab810b80366 · report
mpjpe_cal Vegetebird/MHFormer/common/utils.py official repository unverified MIT (permissive) · c5148aea3c7b76b6 · report
normalize_screen_coordinates Vegetebird/MHFormer/common/camera.py official repository unverified MIT (permissive) · 82baf6aa4fb040a1 · report
test_calculation Vegetebird/MHFormer/common/utils.py official repository unverified MIT (permissive) · d8222b9b5b8b97c9 · report
world_to_camera Vegetebird/MHFormer/common/camera.py official repository unverified MIT (permissive) · 32eca53ede0ea499 · report

Tasks

3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M MHFormer Average MPJPE (mm) 43 #27 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MHFormer Multi-View or Monocular Monocular #27 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MHFormer Using 2D ground-truth joints No #27 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MHFormer AUC 63.3 #25 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MHFormer MPJPE 58 #25 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MHFormer PCK 93.8 #25 of 108 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 EncodingsAdamAttentionBPEDense 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