Papers › Ordinal Depth Supervision for 3D Human Pose Estimation
Ordinal Depth Supervision for 3D Human Pose Estimation
Georgios Pavlakos, Xiaowei Zhou, Kostas Daniilidis
Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap) systems in a studio setting and it is difficult to reach the variability of 2D human pose datasets, like MPII or LSP. To alleviate the need for accurate 3D ground truth, we propose to use a weaker supervision signal provided by the ordinal depths of human joints. This information can be acquired by human annotators for a wide range of images and poses. We showcase the effectiveness and flexibility of training Convolutional Networks (ConvNets) with these ordinal relations in different settings, always achieving competitive performance with ConvNets trained with accurate 3D joint coordinates. Additionally, to demonstrate the potential of the approach, we augment the popular LSP and MPII datasets with ordinal depth annotations. This extension allows us to present quantitative and qualitative evaluation in non-studio conditions. Simultaneously, these ordinal annotations can be easily incorporated in the training procedure of typical ConvNets for 3D human pose. Through this inclusion we achieve new state-of-the-art performance for the relevant benchmarks and validate the effectiveness of ordinal depth supervision for 3D human pose.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Human Pose Estimation | HumanEva-I | Ordinal Depth Supervision | Mean Reconstruction Error (mm) | 18.3 | #8 of 31 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | Ordinal Depth Supervision | AUC | 35.3 | #100 of 108 | Archive leaderboard | report |
| 3D Human Pose Estimation | MPI-INF-3DHP | Ordinal Depth Supervision | PCK | 71.9 | #100 of 108 | Archive leaderboard | report |
| Monocular 3D Human Pose Estimation | Human3.6M | Ordinal Depth Supervision | Frames Needed | 1 | #44 of 52 | Archive leaderboard | report |
| Monocular 3D Human Pose Estimation | Human3.6M | Ordinal Depth Supervision | Need Ground Truth 2D Pose | No | #44 of 52 | Archive leaderboard | report |
| Monocular 3D Human Pose Estimation | Human3.6M | Ordinal Depth Supervision | Use Video Sequence | No | #44 of 52 | 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