Papers › On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation

29 Mar 2022arXiv:2203.15865archive 2025-07-28

Soumava Kumar Roy, Leonardo Citraro, Sina Honari, Pascal Fua

Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labor intensive and time consuming, recent attention has shifted towards semi- and weakly-supervised learning. Generating an effective form of supervision with little annotations still poses major challenge in crowded scenes. In this paper we propose to impose multi-view geometrical constraints by means of a weighted differentiable triangulation and use it as a form of self-supervision when no labels are available. We therefore train a 2D pose estimator in such a way that its predictions correspond to the re-projection of the triangulated 3D pose and train an auxiliary network on them to produce the final 3D poses. We complement the triangulation with a weighting mechanism that alleviates the impact of noisy predictions caused by self-occlusion or occlusion from other subjects. We demonstrate the effectiveness of our semi-supervised approach on Human3.6M and MPI-INF-3DHP datasets, as well as on a new multi-view multi-person dataset that features occlusion.

PaperPDF

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

3D Human Pose Estimation3D Pose EstimationFormPose EstimationWeakly-supervised 3D Human Pose EstimationWeakly-supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Weakly-supervised 3D Human Pose Estimation Human3.6M Triangulation Average MPJPE (mm) 64.7 #16 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation Human3.6M Triangulation PA-MPJPE 52.1 #16 of 33 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation MPI-INF-3DHP Triangulation MPJPE 118.4 #2 of 3 Archive leaderboard report
Weakly-supervised 3D Human Pose Estimation MPI-INF-3DHP Triangulation PCK 73.4 #2 of 3 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