Saved in:
Bibliographic Details
Main Authors: Zheng, Shuntian, Li, Jiaqi, Ni, Minzhe, Lu, Xiaoman, Guan, Yu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.08236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915846274678784
author Zheng, Shuntian
Li, Jiaqi
Ni, Minzhe
Lu, Xiaoman
Guan, Yu
author_facet Zheng, Shuntian
Li, Jiaqi
Ni, Minzhe
Lu, Xiaoman
Guan, Yu
contents We revisit millimeter-wave (mmWave) human pose estimation (HPE) from a signal preprocessing perspective. A single mmWave frame provides structured dimensions that map directly to human geometry and motion: range, angle, and Doppler, offering pose-aligned cues that are not explicitly present in RGB images. However, recent mmWave-based HPE systems require more parameters and compute resources yet yield lower estimation accuracy than vision baselines. We attribute this to preprocessing modules: most systems rely on data-driven modules to estimate phenomena that are already well-defined by mmWave sensing physics, whereas human pose could be captured more efficiently with explicit physical priors. To this end, we introduce processing modules that explicitly model mmWave's inter-dimensional correlations and human kinematics. Our design (1) couples range and angle to preserve spatial human structure, (2) leverages Doppler to retain human motion continuity, and (3) applies multi-scale fusion aligned with the human body. A lightweight MLP is involved as the regressor. In experiments, this framework reduces the number of parameters by 55.7-88.9% on the HPE task relative to existing mmWave baselines while maintaining competitive accuracy. Meanwhile, its lightweight nature enables real-time Raspberry Pi deployment. Code and deployment artifacts will be released upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08236
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Why Learn What Physics Already Knows? Realizing Agile mmWave-based Human Pose Estimation via Physics-Guided Preprocessing
Zheng, Shuntian
Li, Jiaqi
Ni, Minzhe
Lu, Xiaoman
Guan, Yu
Human-Computer Interaction
Hardware Architecture
We revisit millimeter-wave (mmWave) human pose estimation (HPE) from a signal preprocessing perspective. A single mmWave frame provides structured dimensions that map directly to human geometry and motion: range, angle, and Doppler, offering pose-aligned cues that are not explicitly present in RGB images. However, recent mmWave-based HPE systems require more parameters and compute resources yet yield lower estimation accuracy than vision baselines. We attribute this to preprocessing modules: most systems rely on data-driven modules to estimate phenomena that are already well-defined by mmWave sensing physics, whereas human pose could be captured more efficiently with explicit physical priors. To this end, we introduce processing modules that explicitly model mmWave's inter-dimensional correlations and human kinematics. Our design (1) couples range and angle to preserve spatial human structure, (2) leverages Doppler to retain human motion continuity, and (3) applies multi-scale fusion aligned with the human body. A lightweight MLP is involved as the regressor. In experiments, this framework reduces the number of parameters by 55.7-88.9% on the HPE task relative to existing mmWave baselines while maintaining competitive accuracy. Meanwhile, its lightweight nature enables real-time Raspberry Pi deployment. Code and deployment artifacts will be released upon acceptance.
title Why Learn What Physics Already Knows? Realizing Agile mmWave-based Human Pose Estimation via Physics-Guided Preprocessing
topic Human-Computer Interaction
Hardware Architecture
url https://arxiv.org/abs/2603.08236