Papers › Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for...
Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Sebastian Lutz, Richard Blythman, Koustav Ghosal, Matthew Moynihan, Ciaran Simms, Aljosa Smolic
Monocular 3D human pose estimation technologies have the potential to greatly increase the availability of human movement data. The best-performing models for single-image 2D-3D lifting use graph convolutional networks (GCNs) that typically require some manual input to define the relationships between different body joints. We propose a novel transformer-based approach that uses the more generalised self-attention mechanism to learn these relationships within a sequence of tokens representing joints. We find that the use of intermediate supervision, as well as residual connections between the stacked encoders benefits performance. We also suggest that using error prediction as part of a multi-task learning framework improves performance by allowing the network to compensate for its confidence level. We perform extensive ablation studies to show that each of our contributions increases performance. Furthermore, we show that our approach outperforms the recent state of the art for single-frame 3D human pose estimation by a large margin. Our code and trained models are made publicly available on Github.
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 | H3WB | Jointformer-flip | MPJPE | 63.0 | #4 of 17 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | Jointformer (CPN) | Average MPJPE (mm) | 50.5 | #65 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | Jointformer (CPN) | Multi-View or Monocular | Monocular | #65 of 88 | Archive leaderboard | report |
| 3D Human Pose Estimation | Human3.6M | Jointformer (CPN) | Using 2D ground-truth joints | No | #65 of 88 | 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