</> Code with Papers by Syntology

Papers › CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild

30 Nov 2020CVPR 2021 1arXiv:2011.14679archive 2025-07-28

Bastian Wandt, Marco Rudolph, Petrissa Zell, Helge Rhodin, Bodo Rosenhahn

Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately. Unfortunately, for many human activities (\eg outdoor sports) such training data does not exist and is hard or even impossible to acquire with traditional motion capture systems. We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. To this end, we exploit multi-view consistency constraints to disentangle the observed 2D pose into the underlying 3D pose and camera rotation. In contrast to most existing methods, we do not require calibrated cameras and can therefore learn from moving cameras. Nevertheless, in the case of a static camera setup, we present an optional extension to include constant relative camera rotations over multiple views into our framework. Key to the success are new, unbiased reconstruction objectives that mix information across views and training samples. The proposed approach is evaluated on two benchmark datasets (Human3.6M and MPII-INF-3DHP) and on the in-the-wild SkiPose dataset.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bastianwandt/CanonPose officialmentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

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

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M CanonPose Average MPJPE (mm) 74.3 #88 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M CanonPose Multi-View or Monocular MultiView #88 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M CanonPose Using 2D ground-truth joints No #88 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP CanonPose MPJPE 104 #71 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP CanonPose PCK 77 #71 of 108 Archive leaderboard report
3D Human Pose Estimation SkiPose CanonPose CPS 108.7 #3 of 3 Archive leaderboard report
3D Human Pose Estimation SkiPose CanonPose MPJPE 128.1 #3 of 3 Archive leaderboard report
3D Human Pose Estimation SkiPose CanonPose P-MPJPE 89.6 #3 of 3 Archive leaderboard report
3D Human Pose Estimation SkiPose CanonPose PCK 67.1 #3 of 3 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M CanonPose 3D Annotations No #19 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M CanonPose Average MPJPE (mm) 74.3 #19 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M CanonPose Number of Frames Per View 1 #19 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M CanonPose Number of Views 1 #19 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