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

TL;DR

WiCompass is introduced, a coverage-aware data-collection framework that quantifies dataset redundancy and identifies underrepresented motions that quantifies dataset redundancy and identifies underrepresented motions in mmWave sensing.

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.

Figures (13)

• Figure 1: An overview of the pilot studies. (a) illustrates the relationship between model performance and size. (b) shows the results of leave-one-out generalization tests. (c) demonstrates the data efficiency of existing datasets.
• Figure 2: WiCompass Overview. Human poses of SMPL-X format from MoCap datasets and mmWave datasets are encoded into a shared latent space via VQ-VAE. Directional $k$-NN coverage identifies uncovered regions, which then guides pose-conditioned data collection in real or simulated settings.
• Figure 3: VQ-VAE Model Architecture.
• Figure 4: $k$-NN Coverage in the Latent Space.
• Figure 5: Coverage-driven Data Collection Workflow.