Papers › Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

11 Apr 2019CVPR 2019 6arXiv:1904.05547archive 2025-07-28

Chen Li, Gim Hee Lee

3D human pose estimation from a monocular image or 2D joints is an ill-posed problem because of depth ambiguity and occluded joints. We argue that 3D human pose estimation from a monocular input is an inverse problem where multiple feasible solutions can exist. In this paper, we propose a novel approach to generate multiple feasible hypotheses of the 3D pose from 2D joints.In contrast to existing deep learning approaches which minimize a mean square error based on an unimodal Gaussian distribution, our method is able to generate multiple feasible hypotheses of 3D pose based on a multimodal mixture density networks. Our experiments show that the 3D poses estimated by our approach from an input of 2D joints are consistent in 2D reprojections, which supports our argument that multiple solutions exist for the 2D-to-3D inverse problem. Furthermore, we show state-of-the-art performance on the Human3.6M dataset in both best hypothesis and multi-view settings, and we demonstrate the generalization capacity of our model by testing on the MPII and MPI-INF-3DHP datasets. Our code is available at the project website.

PaperPDFConference PDFCodeCode 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 11 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 6 ran (5 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network officialmentioned in papermentioned on GitHubtfMITSyntology: 11 samples, 6 ran (1 instrument-failed) · 5 unverified report
vnmr/JointVideoPose3D mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested 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: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures 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
5ran
5unverified

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 chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network. “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.

chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network official repository 11 samples, 6 ran (1 instrument-failed) · 5 unverified
camera_to_world_frame src/cameras.py ran MIT (permissive) · 6ce042354cb0a857 · report fixture: signature P:ndarray/2/float, R:ndarray/2/float, T:ndarray/2/float · returned ndarray · level recorded 2026-09-25
compute_similarity_transform src/procrustes.py ran MIT (permissive) · d15a574f20fa5bea · report fixture: signature X:ndarray/2/float, Y:ndarray/2/float, compute_optimal_scale:bool/0/bool · returned tuple · level recorded 2026-09-25
get_action_subset src/predict_3dpose_mdm.py ran · our draft was wrong MIT (permissive) · f5eee6f4a7a2d3ce · report fixture: signature poses_set:dict/0/?, action:str/0/str · returned dict · level recorded 2026-09-22
load_data in 700 papers src/data_utils.py ran MIT (permissive) · eba040e815a85e27 · report fixture: signature bpath:str/0/str, subjects:list/1/int, actions:list/1/str, dim:int/0/int · returned dict · level recorded 2026-09-25
project_point_radial src/cameras.py ran MIT (permissive) · b4846342f739f10e · report fixture: signature P:ndarray/2/float, R:ndarray/2/float, T:ndarray/2/float, f:float/0/float, c:ndarray/2/float, k:ndarray/2/float, p:ndarray/2/float · returned tuple · level recorded 2026-09-25
world_to_camera_frame src/cameras.py ran MIT (permissive) · c30df769883845b6 · report fixture: signature P:ndarray/2/float, R:ndarray/2/float, T:ndarray/2/float · returned ndarray · level recorded 2026-09-25
Dirichlet_loss src/mix_den_model.py unverified MIT (permissive) · de6eedce004eb352 · report
kaiming src/mix_den_model.py unverified MIT (permissive) · a8756021030e5968 · report
load_stacked_hourglass src/data_utils.py unverified MIT (permissive) · 32d5f4c81b3b566f · report
mean_log_Gaussian_like src/mix_den_model.py unverified MIT (permissive) · a866706041e55d76 · report
normalization_stats src/data_utils.py unverified MIT (permissive) · 9088d315ea27a453 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose EstimationMulti-Hypotheses 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M MDN (Multi-View) Average MPJPE (mm) 49.6 #61 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN (Multi-View) Multi-View or Monocular Multi-View #61 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN (Multi-View) Using 2D ground-truth joints No #61 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN Average MPJPE (mm) 52.7 #77 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN Multi-View or Monocular Monocular #77 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN PA-MPJPE 42.6 #77 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MDN Using 2D ground-truth joints No #77 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MDM PCK 67.9 #107 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Multimodal Mixture Density Networks Average MPJPE (mm) 52.7 #27 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Multimodal Mixture Density Networks Frames Needed 1 #27 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Multimodal Mixture Density Networks Need Ground Truth 2D Pose No #27 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M Multimodal Mixture Density Networks Use Video Sequence No #27 of 52 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M SMPL-MDN (by 3D Multi-bodies) Best-Hypothesis MPJPE (n = 25) 91.5 #5 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M SMPL-MDN (by 3D Multi-bodies) Best-Hypothesis PMPJPE (n = 25) 69.5 #5 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M SMPL-MDN (by 3D Multi-bodies) H36M PMPJPE (n = 1) 44.8 #5 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M SMPL-MDN (by 3D Multi-bodies) H36M PMPJPE (n = 25) 42.7 #5 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation AH36M SMPL-MDN (by 3D Multi-bodies) Most-Likely Hypothesis PMPJPE (n = 1) 74.7 #5 of 10 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation Human3.6M MDN Average MPJPE (mm) 52.7 #9 of 12 Archive leaderboard report
Multi-Hypotheses 3D Human Pose Estimation Human3.6M MDN Average PMPJPE (mm) 42.6 #9 of 12 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.

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