Uncertainty-Aware Mapping from 3D Keypoints to Anatomical Landmarks for Markerless Biomechanics

TL;DR

This paper demonstrates that modeling predictive uncertainty in 3D keypoint to landmark mapping enhances quality control in markerless biomechanics, enabling reliable frame filtering and failure detection.

Contribution

It introduces a temporal learning framework that models both observation noise and model uncertainty, showing that model uncertainty correlates strongly with landmark errors.

Findings

Uncertainty estimates correlate with landmark error (Spearman ρ ≈ 0.63).

Reliable frame selection reduces error to approximately 16.8 mm at 10% coverage.

Uncertainty effectively detects severe failures with ROC-AUC ≈ 0.92.

Abstract

Markerless biomechanics increasingly relies on 3D skeletal keypoints extracted from video, yet downstream biomechanical mappings typically treat these estimates as deterministic, providing no principled mechanism for frame-wise quality control. In this work, we investigate predictive uncertainty as a quantitative measure of confidence for mapping 3D pose keypoints to 3D anatomical landmarks, a critical step preceding inverse kinematics and musculoskeletal analysis. Within a temporal learning framework, we model both uncertainty arising from observation noise and uncertainty related to model limitations. Using synchronized motion capture ground truth on AMASS, we evaluate uncertainty at frame and joint level through error--uncertainty rank correlation, risk--coverage analysis, and catastrophic outlier detection. Across experiments, uncertainty estimates, particularly those associated with model uncertainty, exhibit a strong monotonic association with landmark error (Spearman $\rho \approx 0.63$), enabling selective retention of reliable frames (error reduced to $\approx 16.8$ mm at 10% coverage) and accurate detection of severe failures (ROC-AUC $\approx 0.92$ for errors $>50$ mm). Reliability ranking remains stable under controlled input degradation, including Gaussian noise and simulated missing joints. In contrast, uncertainty attributable to observation noise provides limited additional benefit in this setting, suggesting that dominant failures in keypoint-to-landmark mapping are driven primarily by model uncertainty. Our results establish predictive uncertainty as a practical, frame-wise tool for automatic quality control in markerless biomechanical pipelines.