Papers › Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates

Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates

21 Nov 2019arXiv:1911.09245archive 2025-07-28

Diogo C. Luvizon, Hedi Tabia, David Picard

3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D annotated data and 3D poses and a straightforward multi-view generalization. To that end, we cast the problem as a view frustum space pose estimation, where absolute depth prediction and joint relative depth estimations are disentangled. Final 3D predictions are obtained in camera coordinates by the inverse camera projection. Based on this, we also present a consensus-based optimization algorithm for multi-view predictions from uncalibrated images, which requires a single monocular training procedure. Although our method is indirectly tied to the training camera intrinsics, it still converges for cameras with different intrinsic parameters, resulting in coherent estimations up to a scale factor. Our method improves the state of the art on well known 3D human pose datasets, reducing the prediction error by 32% in the most common benchmark. We also reported our results in absolute pose position error, achieving 80~mm for monocular estimations and 51~mm for multi-view, on average.

PaperPDFCode

Code

dluvizon/3d-pose-consensus officialmentioned in papermentioned on GitHub 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 EstimationDepth EstimationDepth PredictionPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, GT calib.) Average MPJPE (mm) 39 #16 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, GT calib.) Multi-View or Monocular Multi-View #16 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, GT calib.) Using 2D ground-truth joints No #16 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, est. calib.) Average MPJPE (mm) 45 #43 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, est. calib.) Multi-View or Monocular Multi-View #43 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (multi-view, est. calib.) Using 2D ground-truth joints No #43 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (monocular) Average MPJPE (mm) 52 #74 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (monocular) Multi-View or Monocular Monocular #74 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M Pose Consensus (monocular) Using 2D ground-truth joints No #74 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP Pose Consensus (monocular) AUC 42.1 #77 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP Pose Consensus (monocular) MPJPE 112.1 #77 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP Pose Consensus (monocular) PCK 80.6 #77 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.

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