Papers › Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry

Self-Supervised 3D Human Pose Estimation with Multiple-View Geometry

17 Aug 2021arXiv:2108.07777archive 2025-07-28

Arij Bouazizi, Julian Wiederer, Ulrich Kressel, Vasileios Belagiannis

We present a self-supervised learning algorithm for 3D human pose estimation of a single person based on a multiple-view camera system and 2D body pose estimates for each view. To train our model, represented by a deep neural network, we propose a four-loss function learning algorithm, which does not require any 2D or 3D body pose ground-truth. The proposed loss functions make use of the multiple-view geometry to reconstruct 3D body pose estimates and impose body pose constraints across the camera views. Our approach utilizes all available camera views during training, while the inference is single-view. In our evaluations, we show promising performance on Human3.6M and HumanEva benchmarks, while we also present a generalization study on MPI-INF-3DHP dataset, as well as several ablation results. Overall, we outperform all self-supervised learning methods and reach comparable results to supervised and weakly-supervised learning approaches. Our code and models are publicly available

Paper PDF Code

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

Code

vru2020/Pose_3D 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 Estimation Pose Estimation Self-Supervised Learning Weakly-supervised 3D Human Pose Estimation Weakly-supervised Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Average MPJPE (mm)	62.0	#84 of 88	Archive leaderboard	report
3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Multi-View or Monocular	Multi-View	#84 of 88	Archive leaderboard	report
3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Using 2D ground-truth joints	No	#84 of 88	Archive leaderboard	report
Weakly-supervised 3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	3D Annotations	No	#12 of 33	Archive leaderboard	report
Weakly-supervised 3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Average MPJPE (mm)	62.0	#12 of 33	Archive leaderboard	report
Weakly-supervised 3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Number of Frames Per View	1	#12 of 33	Archive leaderboard	report
Weakly-supervised 3D Human Pose Estimation	Human3.6M	2D-3D Lifting self-supervised	Number of Views	1	#12 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