Papers › Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
Paweł A. Pierzchlewicz, R. James Cotton, Mohammad Bashiri, Fabian H. Sinz
Due to depth ambiguities and occlusions, lifting 2D poses to 3D is a highly ill-posed problem. Well-calibrated distributions of possible poses can make these ambiguities explicit and preserve the resulting uncertainty for downstream tasks. This study shows that previous attempts, which account for these ambiguities via multiple hypotheses generation, produce miscalibrated distributions. We identify that miscalibration can be attributed to the use of sample-based metrics such as minMPJPE. In a series of simulations, we show that minimizing minMPJPE, as commonly done, should converge to the correct mean prediction. However, it fails to correctly capture the uncertainty, thus resulting in a miscalibrated distribution. To mitigate this problem, we propose an accurate and well-calibrated model called Conditional Graph Normalizing Flow (cGNFs). Our model is structured such that a single cGNF can estimate both conditional and marginal densities within the same model - effectively solving a zero-shot density estimation problem. We evaluate cGNF on the Human~3.6M dataset and show that cGNF provides a well-calibrated distribution estimate while being close to state-of-the-art in terms of overall minMPJPE. Furthermore, cGNF outperforms previous methods on occluded joints while it remains well-calibrated.
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 |
|---|---|---|---|---|---|---|---|
| Multi-Hypotheses 3D Human Pose Estimation | Human3.6M | cGNF xlarge w Lsample | Average MPJPE (mm) | 48.5 | #8 of 12 | Archive leaderboard | report |
| Multi-Hypotheses 3D Human Pose Estimation | Human3.6M | cGNF w Lsample | Average MPJPE (mm) | 53 | #10 of 12 | Archive leaderboard | report |
| Multi-Hypotheses 3D Human Pose Estimation | Human3.6M | cGNF w Lsample | Average MPJPE (mm) for occluded Joints | 41.8 | #10 of 12 | Archive leaderboard | report |
| Multi-Hypotheses 3D Human Pose Estimation | Human3.6M | cGNF w Lsample | Expected Calibration Error | 0.08 | #10 of 12 | 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