Re-evaluating Position and Velocity Decoding for Hand Pose Estimation with Surface Electromyography

TL;DR

This study reevaluates hand pose estimation from surface electromyography, demonstrating that with proper tuning, position decoding surpasses velocity decoding in accuracy and robustness, challenging previous conclusions.

Contribution

The paper shows that position decoding outperforms velocity decoding when properly tuned, revising prior benchmark conclusions and establishing new state-of-the-art results.

Findings

Position decoding outperforms velocity decoding after tuning.

Multi-task training improves regression task performance.

A speed-adaptive filter enhances smoothness-accuracy tradeoff.

Abstract

Recent progress in real-time hand pose estimation from surface electromyography (sEMG) has been driven by the emg2pose benchmark, whose original baseline study concluded that velocity decoding outperforms position decoding in both reconstruction accuracy and trajectory smoothness. We revisit that conclusion under the original causal evaluation protocol. Using the same core architecture but a more stable training recipe, we show that position decoding models were previously underestimated because they are highly sensitive to a previously unswept decoder output scalar and can otherwise collapse into low movement solutions. Once this scalar is tuned, position decoding outperforms velocity decoding on the Tracking task across all three emg2pose generalization conditions, consistent with greater robustness to error accumulation. On the Regression task, the gap between position and velocity decoding is much smaller; instead, the largest gains come from multi-task training with Tracking, suggesting that the Regression objective alone does not sufficiently constrain the learned dynamics. Although position decoding models exhibit greater local jitter, a causal speed-adaptive filter preserves their accuracy advantage while yielding a more favorable smoothness-accuracy tradeoff than velocity decoding. Altogether, our results revise the original emg2pose modeling conclusions and establish a new state of the art among published streaming-compatible models on this benchmark.