Papers › 3D human pose estimation in video with temporal convolutions and semi-supervised training

3D human pose estimation in video with temporal convolutions and semi-supervised training

28 Nov 2018CVPR 2019 6arXiv:1811.11742archive 2025-07-28

Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli

In this work, we demonstrate that 3D poses in video can be effectively estimated with a fully convolutional model based on dilated temporal convolutions over 2D keypoints. We also introduce back-projection, a simple and effective semi-supervised training method that leverages unlabeled video data. We start with predicted 2D keypoints for unlabeled video, then estimate 3D poses and finally back-project to the input 2D keypoints. In the supervised setting, our fully-convolutional model outperforms the previous best result from the literature by 6 mm mean per-joint position error on Human3.6M, corresponding to an error reduction of 11%, and the model also shows significant improvements on HumanEva-I. Moreover, experiments with back-projection show that it comfortably outperforms previous state-of-the-art results in semi-supervised settings where labeled data is scarce. Code and models are available at https://github.com/facebookresearch/VideoPose3D

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="1811.11742")

Code

Syntology Ran 0 of 2 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run.

By repository: official repository: 1 sample from 1 repository, 0 ran; community (archive-listed): 1 sample from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

facebookresearch/VideoPose3D officialmentioned in papermentioned on GitHubpytorch report
ailingzengzzz/Split-and-Recombine-Net mentioned on GitHubpytorchApache-2.0 report
garyzhao/SemGCN mentioned on GitHubpytorchApache-2.0 report
happyvictor008/High-order-GNN-LF-iter mentioned on GitHubpytorch report
philipNoonan/OPVP3D mentioned on GitHubpytorch report
raymondyeh07/chirality_nets mentioned on GitHubpytorchMIT report
sjtuxcx/ITES mentioned on GitHubpytorch report
vnmr/JointVideoPose3D mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-ready report
zhimingzo/modulated-gcn mentioned on GitHubpytorch report
open-mmlab/mmpose pytorchApache-2.0 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

2 samples harvested; 0 ran; 0 honoured the contract we drafted; 2 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.

2unverified

Licence: 2 of the 2 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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_resolution facebookresearch/VideoPose3D/inference/infer_video.py official repository unverified licence not identified · pointer only · 3796316610a45f92 · report
evaluate philipNoonan/OPVP3D/run_wild.py community (archive-listed) unverified licence not identified · pointer only · 507ee77c01d06e70 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose EstimationWeakly-supervised 3D Human Pose Estimation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Average MPJPE (mm) 46.8 #49 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Multi-View or Monocular Monocular #49 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=243) PA-MPJPE 36.5 #49 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Using 2D ground-truth joints No #49 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=1) Average MPJPE (mm) 51.8 #72 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=1) Multi-View or Monocular Monocular #72 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=1) PA-MPJPE 40 #72 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M VideoPose3D (T=1) Using 2D ground-truth joints No #72 of 88 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) 2D detector CPN #20 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Average MPJPE (mm) 46.8 #20 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Frames Needed 243 #20 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Need Ground Truth 2D Pose No #20 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Use Video Sequence Yes #20 of 52 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M Pavllo et al. 3D Annotations S1 #15 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M Pavllo et al. Average MPJPE (mm) 64.7 #15 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M Pavllo et al. Number of Views 1 #15 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M VideoPose3D (T=243) Number of Frames Per View 243 #32 of 33 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