High-resolution efficient image generation from WiFi Mapping
5 hours ago
- #Computer Vision
- #WiFi Imaging
- #Latent Diffusion Models
- LatentCSI is a novel method for generating images from WiFi CSI measurements using a pretrained latent diffusion model (LDM).
- The method employs a lightweight neural network to map CSI amplitudes into the latent space of an LDM, bypassing pixel-space image generation challenges.
- LatentCSI avoids the explicit image encoding stage typically required in conventional image-to-image pipelines, enabling efficient and high-quality image synthesis.
- The approach is validated on two datasets: a wide-band CSI dataset collected with off-the-shelf WiFi devices and cameras, and a subset of the MM-Fi dataset.
- Results show that LatentCSI outperforms baselines in computational efficiency and perceptual quality, with added text-guided controllability.