WiCompass: Oracle-driven Data Scaling for mmWave Human Pose Estimation

2026-02-21

AI Summary

This work addresses the limited generalization of millimeter-wave human pose estimation under distribution shifts, a challenge exacerbated by the inefficiency and insufficient coverage of conventional data augmentation techniques. To overcome this, the authors propose WiCompass, a novel framework that introduces a coverage-aware data collection paradigm. WiCompass leverages a large-scale motion capture dataset to construct a universal pose-space oracle and employs a closed-loop active sampling strategy to prioritize the acquisition of informative samples that fill critical coverage gaps. By shifting data expansion from indiscriminate volume accumulation to targeted deficiency remediation, the method significantly enhances model accuracy and robustness in out-of-distribution scenarios under identical data budgets.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Active Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Millimeter-wave Human Pose Estimation (mmWave HPE) promises privacy but suffers from poor generalization under distribution shifts. We demonstrate that brute-force data scaling is ineffective for out-of-distribution (OOD) robustness; efficiency and coverage are the true bottlenecks. To address this, we introduce WiCompass, a coverage-aware data-collection framework. WiCompass leverages large-scale motion-capture corpora to build a universal pose space ``oracle'' that quantifies dataset redundancy and identifies underrepresented motions. Guided by this oracle, WiCompass employs a closed-loop policy to prioritize collecting informative missing samples. Experiments show that WiCompass consistently improves OOD accuracy at matched budgets and exhibits superior scaling behavior compared to conventional collection strategies. By shifting focus from brute-force scaling to coverage-aware data acquisition, this work offers a practical path toward robust mmWave sensing.

Problem

• mmWave Human Pose Estimation
• distribution shift
• out-of-distribution robustness
• data scaling
• pose coverage

Innovation

• coverage-aware data collection
• mmWave human pose estimation
• out-of-distribution robustness
• oracle-guided sampling
• data efficiency