mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Jiarui, Xia, Songpengcheng, Lai, Zengyuan, Sun, Lan, Wu, Qi, Yu, Wenxian, Pei, Ling
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912257772879872
author Yang, Jiarui
Xia, Songpengcheng
Lai, Zengyuan
Sun, Lan
Wu, Qi
Yu, Wenxian
Pei, Ling
author_facet Yang, Jiarui
Xia, Songpengcheng
Lai, Zengyuan
Sun, Lan
Wu, Qi
Yu, Wenxian
Pei, Ling
contents Millimeter-wave (mmWave) radar offers robust sensing capabilities in diverse environments, making it a highly promising solution for human body reconstruction due to its privacy-friendly and non-intrusive nature. However, the significant sparsity of mmWave point clouds limits the estimation accuracy. To overcome this challenge, we propose a two-stage deep learning framework that enhances mmWave point clouds and improves human body reconstruction accuracy. Our method includes a mmWave point cloud enhancement module that densifies the raw data by leveraging temporal features and a multi-stage completion network, followed by a 2D-3D fusion module that extracts both 2D and 3D motion features to refine SMPL parameters. The mmWave point cloud enhancement module learns the detailed shape and posture information from 2D human masks in single-view images. However, image-based supervision is involved only during the training phase, and the inference relies solely on sparse point clouds to maintain privacy. Experiments on multiple datasets demonstrate that our approach outperforms state-of-the-art methods, with the enhanced point clouds further improving performance when integrated into existing models.
format Preprint
id arxiv_https___arxiv_org_abs_2503_02375
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction
Yang, Jiarui
Xia, Songpengcheng
Lai, Zengyuan
Sun, Lan
Wu, Qi
Yu, Wenxian
Pei, Ling
Computer Vision and Pattern Recognition
Millimeter-wave (mmWave) radar offers robust sensing capabilities in diverse environments, making it a highly promising solution for human body reconstruction due to its privacy-friendly and non-intrusive nature. However, the significant sparsity of mmWave point clouds limits the estimation accuracy. To overcome this challenge, we propose a two-stage deep learning framework that enhances mmWave point clouds and improves human body reconstruction accuracy. Our method includes a mmWave point cloud enhancement module that densifies the raw data by leveraging temporal features and a multi-stage completion network, followed by a 2D-3D fusion module that extracts both 2D and 3D motion features to refine SMPL parameters. The mmWave point cloud enhancement module learns the detailed shape and posture information from 2D human masks in single-view images. However, image-based supervision is involved only during the training phase, and the inference relies solely on sparse point clouds to maintain privacy. Experiments on multiple datasets demonstrate that our approach outperforms state-of-the-art methods, with the enhanced point clouds further improving performance when integrated into existing models.
title mmDEAR: mmWave Point Cloud Density Enhancement for Accurate Human Body Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.02375