PressureMesh: 3D Human Mesh Estimation from Multi-Device Pressure Images
2026-08-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on tracking human body positions using pressure sensors, which are good at protecting privacy. They note that most current methods use just one sensor device, limiting how much of the body can be monitored. To improve this, the authors created MDP-Net, a system that combines data from multiple pressure sensors to better estimate human body shapes over time. They also made a new dataset with various pose labels to train and test their system. Their tests showed that combining information from several devices helps monitor body poses more accurately.
human pose monitoringpressure sensorsMixture of Experts (MoE)multi-device fusionhuman mesh estimationtemporal pressure data2D/3D joint detectionrehabilitation assessmentprivacy-preserving sensingend-to-end neural network
Authors
Changhai Ma, Ziyu Wu, Yunkang Zhang, Fangting Xie, Mengting Niu, Heyu Ding, Quan Wan, Jiayue Yuan, Boyan Liu, Yi Ke, Xiaohui Cai
Abstract
Human pose monitoring is crucial in fields such as rehabilitation assessment and human-computer interaction. Due to its privacy-preserving nature, pressure-based human pose monitoring has become a primary approach for unobtrusive sensing. However, existing methods are generally limited to a single device, which restricts the effective monitoring range. To address this limitation, we propose MDP-Net, an end-to-end network capable of directly estimating human meshes from temporal pressure data across multiple devices. We introduce a multimodal fusion mechanism inspired by the Mixture of Experts (MoE) framework to achieve effective complementarity and enhancement of cross-device pressure information. To support the training and evaluation of MDP-Net, we constructed MDP, a high-quality multi-device temporal pressure dataset that includes various pose labels such as 2D/3D joints and human meshes. Experimental results demonstrate that MDP-Net achieves a joint position error of 12.6 cm on the MDP dataset. These results prove that fusing multi-device pressure information is an effective and promising new solution for daily human pose monitoring.