Doppler Prompting for Stable mmWave-based Human Pose Estimation

2026-05-13

AI Summary

Existing millimeter-wave human pose estimation methods inadequately exploit or coarsely fuse Doppler features, rendering them susceptible to interference from non-human motion and resulting in jittery pose trajectories. This work proposes PULSE, a novel approach that models Doppler features as confidence-aware, filterable motion cues and injects them into the spatial amplitude reasoning process through a constrained interaction mechanism, effectively discarding spurious motion signals prior to fusion. By enabling physically meaningful semantic discrimination and controllable integration of modalities, PULSE significantly improves both accuracy and temporal stability of pose estimation across three datasets encompassing both single- and multi-person scenarios.

Abstract

Millimeter-wave (mmWave) enables privacy-preserving, illumination-robust human pose estimation (HPE), with each mmWave frame represented as a range-angle-Doppler tensor, providing spatial magnitude for localization and Doppler signatures for motion-related cues. However, existing mmWave-based HPE methods either underutilize or naïvely fuse Doppler signatures with spatial magnitude, disregarding their distinct physical semantics. As a result, non-human Doppler signatures can be misinterpreted as human motion cues, leading to jittery trajectories. We propose PULSE, which converts Doppler signatures into confidence-aware motion prompts and injects them into spatial magnitude reasoning through constrained interactions. By screening Doppler prompts before they influence prediction, PULSE first suppresses spurious spectral motion cues and then uses the screened prompts to stabilize prediction. Across three datasets spanning single- and multi-person settings, PULSE consistently improves pose accuracy and temporal stability, indicating that controlled Doppler prompting is a practical direction for stable mmWave HPE.

Problem

• mmWave
• human pose estimation
• Doppler signatures
• temporal stability
• motion cues

Innovation

• Doppler prompting
• mmWave human pose estimation
• motion cues
• temporal stability
• confidence-aware fusion