A Two-Stage Motion-Aware Framework for mmWave-based Human Mesh Recovery

2026-05-08

AI Summary

This work addresses the challenges of strong signal clutter and incomplete measurements in millimeter-wave radar-based 3D human mesh reconstruction. The authors propose a two-stage framework: first, a confidence-weighted radar volume representation is constructed through coarse-to-fine reflection point extraction and voxel-level segmentation; subsequently, high-fidelity mesh reconstruction is achieved by fusing single-frame geometric cues with cross-frame motion information. The key innovation lies in decoupling signal parsing from geometric reasoning for the first time, and introducing a dual-branch motion-aware network that jointly models spatiotemporal dynamics. This approach significantly outperforms existing millimeter-wave human reconstruction methods while maintaining computational efficiency.

Abstract

Millimeter-wave (mmWave) radar has emerged as a promising sensing modality for human perception due to its robustness under challenging environmental conditions and strong privacy-preserving properties. However, recovering accurate 3D human body meshes from radar observations remains difficult due to severe signal clutter and the inherently partial nature of radar measurements. Previous works typically adopt end-to-end frameworks that directly regress human body parameters from raw radar data, without decoupling signal interpretation from geometric reasoning or exploiting temporal motion cues, limiting learning performance. To address this, we propose a two-stage framework for radar-based human body reconstruction. First, we introduce a human reflection extraction module that performs coarse-to-fine localization and voxel-wise segmentation to produce a confidence-weighted radar volume encoding voxel-level human likelihood. Second, we design a motion-aware mesh recovery network that reconstructs the human body by jointly modeling per-frame geometry and inter-frame dynamics using a dual-branch architecture. Extensive experiments demonstrate that the proposed method outperforms existing approaches while maintaining computational efficiency.

Problem

• mmWave radar
• human mesh recovery
• signal clutter
• partial measurements
• 3D human body reconstruction

Innovation

• two-stage framework
• motion-aware reconstruction
• mmWave radar
• human mesh recovery
• voxel-wise segmentation