SOURCE-LINKED INTELLIGENCE

Structured Pose-Conditioned Flow Matching for Generative 5G CSI Augmentation

arXiv · AI, language, vision and robotics · article · Sep 24, 2026 · UTC

With the growing demand for privacy-preserving and occlusion-resilient human pose recognition (HPR), 5G channel state information (CSI) offers a promising contactless sensing modality by integrating communication and sensing capabilities. However, collecting large-scale synchronized CSI-pose pairs remains costly in practical 5G systems. To address this limitation, we propose StructFlow-HPR, a structured pose-conditioned flow matching framework for generative CSI augmentation. StructFlow-HPR learns a continuous latent transport process from Gaussian noise to real CSI representations under pose

Read original source ↗ Open in workspace

recordType

paper

region

Global