SuDA: Support-based Domain Adaptation for Sim2Real Motion Capture with Flexible Sensors

TL;DR

SuDA introduces a novel domain adaptation approach for flexible sensor-based human motion capture, eliminating the need for labeled data and achieving accuracy comparable to supervised methods.

Contribution

The paper proposes SuDA, a support-based domain adaptation method that aligns predictive supports instead of distributions, improving Sim2Real MoCap with flexible sensors.

Findings

SuDA outperforms state-of-the-art distribution-based domain adaptation methods.

It achieves comparable accuracy to supervised learning without labeled data.

Experimental results validate the effectiveness of SuDA in MoCap tasks.

Abstract

Flexible sensors hold promise for human motion capture (MoCap), offering advantages such as wearability, privacy preservation, and minimal constraints on natural movement. However, existing flexible sensor-based MoCap methods rely on deep learning and necessitate large and diverse labeled datasets for training. These data typically need to be collected in MoCap studios with specialized equipment and substantial manual labor, making them difficult and expensive to obtain at scale. Thanks to the high-linearity of flexible sensors, we address this challenge by proposing a novel Sim2Real Mocap solution based on domain adaptation, eliminating the need for labeled data yet achieving comparable accuracy to supervised learning. Our solution relies on a novel Support-based Domain Adaptation method, namely SuDA, which aligns the supports of the predictive functions rather than the instance-dependent distributions between the source and target domains. Extensive experimental results demonstrate the effectiveness of our method andits superiority over state-of-the-art distribution-based domain adaptation methods in our task.